Dissertations / Theses: 'Chatbot'

1

Aljadri, Sinan. "Chatbot : A qualitative study of users' experience of Chatbots." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-105434.

Full text

Abstract:

The aim of the present study has been to examine users' experience of Chatbot from a business perspective and a consumer perspective. The study has also focused on highlighting what limitations a Chatbot can have and possible improvements for future development. The study is based on a qualitative research method with semi-structured interviews that have been analyzed on the basis of a thematic analysis. The results of the interview material have been analyzed based on previous research and various theoretical perspectives such as Artificial Intelligence (AI), Natural Language Processing (NLP). The results of the study have shown that the experience of Chatbot can differ between businesses that offer Chatbot, which are more positive and consumers who use it as customer service. Limitations and suggestions for improvements around Chatbotar are also a consistent result of the study.
Den föreliggande studie har haft som syfte att undersöka användarnas upplevelse av Chatbot utifrån verksamhetsperspektiv och konsumentperspektiv. Studien har också fokuserat på att lyfta fram vilka begränsningar en Chatbot kan ha och eventuella förbättringar för framtida utvecklingen. Studien är baserad på en kvalitativ forskningsmetod med semistrukturerade intervjuer som har analyserats utifrån en tematisk analys. Resultatet av intervjumaterialet har analyserat utifrån tidigare forskning och olika teoretiska perspektiv som Artificial Intelligence (AI), Natural Language Processing (NLP). Resultatet av studien har visat att upplevelsen av Chatbot kan skilja sig mellan verksamheter som erbjuder Chatbot, som är mer positiva och konsumenter som använder det som kundtjänst. Begränsningar och förslag på förbättringar kring Chatbotar är också ett genomgående resultat i studien.

APA, Harvard, Vancouver, ISO, and other styles

2

Jusko, Ján. "Chatbot pro Smart Cities." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2019. http://www.nusl.cz/ntk/nusl-403204.

Full text

Abstract:

The aim of this work is to simplify access to information for citizens of the city of Brno and at the same time to innovate the way of communication between the citizen and his city. The problem is solved by creating a conversational agent - chatbot Kroko. Using artificial intelligence and a Czech language analyzer, the agent is able to understand and respond to a certain set of textual, natural language queries. The agent is available on the Messenger platform and has a knowledge base that includes data provided by the city council. After conducting an extensive user testing on a total of 76 citizens of the city, it turned out that up to 97\% of respondents like the idea of a city-oriented chatbot and can imagine using it regularly. The main finding of this work is that the general public can easily adopt and effectively use a chatbot. The results of this work motivate further development of practical applications of conversational agents.

APA, Harvard, Vancouver, ISO, and other styles

3

Jonsson, Sofia, and Jenny Bredmar. "Chatbot - Magic in a box? : A study of a chatbot in a Swedish bank." Thesis, Uppsala universitet, Institutionen för informatik och media, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-355381.

Full text

Abstract:

Artificial Intelligence (AI) is a topic, which is widely discussed around the globe. One branch of AI is Chatbot (CB) technology that uses Natural Language Processing to understand, reply and communicate with humans. Increasingly, CB has gained more popularity in many companies because of its contribution to productivity and efficiency. However, less is said about organizations expectations, use, and challenges of the CB. This exploratory research tries to get a more organizational perspective of this new phenomenon. To do so, we conducted interviews with project members in a large banking organization that utilizes CB. This study contributed three major conclusions: first, the importance of making sure employees understand the importance and scale of training in regard to the use of a chatbot. Second, the results also suggest that the CB performs simple tasks but still has the ability to save time for employees who use it. Third, this study acknowledged the potential in CB and the importance of proactively embracing it today to not fall behind the curve. The result contributes to the research area of CB with insights from an organizational perspective.

APA, Harvard, Vancouver, ISO, and other styles

4

Ahlström, Sara, and Patricia Jansson. "Chatbot den digitalakundtjänstmedarbetaren : En kvalitativ studie kring hur lojalitetsfaktorernapåverkas av konsumentmötet med en chatbot." Thesis, Högskolan i Halmstad, Akademin för ekonomi, teknik och naturvetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-42440.

Full text

Abstract:

Titel: Chattbot den digitala kundtjänstmedarbetaren: En kvalitativ studie kring hur lojalitetsfaktorerna påverkas av konsumentmötet med en chattbot. Ämne: Kandidatuppsats i företagsekonomiinriktning marknadsföring, 15hp Författare: Sara Ahlström & Patricia Jansson Nyckelord: Varumärkeslojalitet, artificiell intelligens, chattbot Syfte: Syftet med studien är att ur ett business-to-consumer perspektiv genomföra en djupgående undersökning av hur faktorerna bakom varumärkeslojalitet påverkas av konsumentmötet med en chattbot. Genom den ökade förståelsen eftersträvas att utveckla ett teoretiskt ramverk. Metod: Studien är av det kvalitativa slaget och har genomförts med en abduktiv forskningsansats. Studiens slutliga resultat grundar sig i genomförda datorbaserade chattintervjuer med konsumenter. Slutsats: Utfallet av studien har utökat förståelsen för hur faktorerna vilka ligger till grund för byggandet av varumärkeslojalitet förändras med den digitala teknologin chattbots. Genom studien har en förståelse för vilka komponenter bakom lojalitetsfaktorerna som är av stor vikt. Viktiga komponenter vilka uppmärksammats är utfallet av chattbotens service-kvalité bestående av kundnöjdhet och förtroende, och kvalité av interaktionen bestående av kommunikation och personlighet Kunskapsbidrag: Praktiska och teoretiska kunskaper kring chattbots påverkan på kundnöjdhet, relationer, kommunikation och avsaknaden av den mänskliga kontakten har lyfts fram. Genom det teoretiska ramverket belyses viktiga delar att ta hänsyn till kring skapandet och utvecklandet av chattbots, vilket är av betydelse för företag som vill skapa en positiv upplevelse i mötet med den digitala medarbetaren

APA, Harvard, Vancouver, ISO, and other styles

5

Roghult, Alexander. "Chatbot trained on movie dialogue." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-157637.

Full text

Abstract:

A chatbot is a computer program that engages in written or spoken conversation with a human user. This project aims to investigate the possibility of training a chatbot in using movie dialogue in generating the response. Movie dialogue can be found in both movie scripts as well as subtitles, though using subtitles is much easier as they follow a special formatting. Using one subtitle as a response to each word found in the preceding subtitle, the implemented chatbot links together subtitles. The responses are stored in a frequency distribution table that maps each word to all responses found. Though the responses generated by the chatbot were not desirable, the responsese tmost often contained responses which would be more fitting. The result drawn from hisis that ,with further work and improvement,the chatbot could perform acceptably

APA, Harvard, Vancouver, ISO, and other styles

6

Amilon, Mattias. "Chatbot with common-sense database." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166745.

Full text

Abstract:

In 1950 Alan Turing introduced the famous “Turing test” which tests if a machine can be as intelligent as a human by testing if it can communicate with a person in a “human” way. Inspired by this test, numerous so called chatbots, in the form of computer programs, that manage a written dialogue have been created. A so called commonsensedatabase consists of data that most humans would know andconsider as common knowledge, something that computers generally do not know very muchabout. This report describes the process of an attempt to implement a simple chatbot using the common-sense database ConceptNet. The behaviour, or the human-likeness, of this chatbot was then compared to that of the classic chatbot ELIZA and the 2008 Loebner prize winning chatbot Elbot, through a series of user tests. The results indicate that using a common-sense database for a chatbot shows some promisefor further investigation.

APA, Harvard, Vancouver, ISO, and other styles

7

Krantz, Amandus, and Petrus Lindblom. "Generating Topic-Based Chatbot Responses." Thesis, Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-14800.

Full text

Abstract:

With the rising popularity of chatbots, not just in entertainment but in e-commerce and online chat support, it’s become increasingly important to be able to quickly set up chatbots that can respond to simple questions. This study examines which of two algorithms for automatic generation of chatbot knowledge bases, First Word Search or Most Signiﬁcant Word Search, is able to generate the responses that are the most relevant to the topic of a question. It also examines how text corpora might be used as a source from which to generate chatbot knowledge bases. Two chatbots were developed for this project, one for each of the two algorithms that are to be examined. The chatbots are evaluated through a survey where the participants are asked to choose which of the algorithms they thought chose the response that was most relevant to a question. Based on the survey we conclude that Most Signiﬁcant Word Search is the algorithm that picks the most relevant responses. Most Signiﬁcant Word Search has a signiﬁcantly higher chance of generating a response that is relevant to the topic. However, how well a text corpus works as a source for knowledge bases depends entirely on the quality and nature of the corpus. A corpus consisting of written dialogue is likely more suitable for conversion into a knowledge base.

APA, Harvard, Vancouver, ISO, and other styles

8

Tor, Kjäll. "Visualization of Chatbot Survey Results." Thesis, Uppsala universitet, Människa-datorinteraktion, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-414841.

Full text

Abstract:

Chatbots are an increasingly popular technique that has seen recent steps in development thanks to artificial intelligence. There is research conducted about chatbots in different areas, but one area that is overlooked is the presentation of data collected by the chatbot. This study aimed to explore what to think about in terms of visualizations when designing an interface in order to present chatbots results to novice users. Conducting a user study with several iterations of design, the research question was: How do you visualize the results of a chatbot survey for novice users to facilitate the understanding of the data? To answer this question, four design iterations with a total of 17 participants were conducted, resulting in a final prototype. The data gathered was then analyzed using thematic analysis. The results failed to help answering the research question, but did give some suggestions on interface visualization, mainly the importance of using visualizations that are carefully selected to improve the understanding of the data presented. Moreover, this study suggests the importance of focusing on the participant’s deeper level of understanding and their conceptual models.

APA, Harvard, Vancouver, ISO, and other styles

9

Novák, Miroslav. "Chatbot v podnikovém informačním systému." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2019. http://www.nusl.cz/ntk/nusl-403114.

Full text

Abstract:

This diploma thesis deals with problems of development of chatbots. The theoretical part of the thesis introduces the concept of the conversational interface in general and analyzes available technologies for its development. The practical part deals with the design and implementation of a particular chatbot, whose goal is to be a virtual assistant in the process of selecting and purchasing goods. This is accomplished by connecting the chatbot to the product information management system using OData web services. One of the biggest problems was to determine the order of questions asked about product properties. For the implementation was used decision tree theory.

APA, Harvard, Vancouver, ISO, and other styles

10

Choque, Díaz Marilyn Lizet. "Chatbot académico utilizando tecnologías cognitivas." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2018. http://hdl.handle.net/10757/624418.

Full text

Abstract:

El presente proyecto “Chatbot académico utilizando tecnologías cognitivas” tiene como objetivo principal implementar un modelo de tecnología cognitiva para mejorar los servicios de soporte académico con chatbots en instituciones universitarias. La diferencia entre los modelos convencionales y el modelo propuesto en este proyecto radica, aparte de basarse en computación cognitiva, en adicionar patrones Customer Experience, los cuales mejoran sustancialmente la interacción que se tiene con el estudiante, así como la experiencia y satisfacción con su institución universitaria. El surgimiento de nuevas tecnologías y la omnipresencia de Internet están brindando oportunidades de nuevas formas de interacción entre clientes y proveedores de servicios. Una de esas tecnologías son los chatbots capaces de responder a consultas del cliente permitiendo ahorrar tiempo y trabajo humano. Los chatbots han abierto una nueva puerta para la comunicación y, sobre todo, en cuanto a la atención al cliente se refiere. Existe una creciente expectación sobre los chatbots y sobre cómo afectarán en el futuro de la experiencia del cliente, ya que se están utilizando cada vez más para liberar a los humanos de sus tareas dentro de un centro de atención al cliente y, aunque parezca contradictorio, están ayudando a brindar una experiencia más personalizada. El aporte de este proyecto es la propuesta de un modelo de tecnología cognitiva para mejorar los servicios de soporte académico con chatbots, que pueda impulsar y potenciar iniciativas que propicien un mayor aprovechamiento de la interacción con el estudiante en la Universidad Peruana de Ciencias Aplicadas (UPC).
This project "Academic chatbot using cognitive technologies" aims to implement a cognitive technology model to enhance academic support services with chatbots at university institutions. The difference between the conventional models and the model proposed in this project lies, apart from being based on cognitive computing, in adding Customer Experience patterns. This could substantially improve the interaction with student, as well as the experience and satisfaction with its university institution. The emergence of new technologies and the pervasiveness of the Internet are providing opportunities for new forms of interaction between customers and service providers. One of these technologies are chatbots capable of responding to customer queries saving time and human work. Chatbots have opened a new door for communication and, above all, in terms of customer service. There is growing expectation about chatbots and how they will affect the future of the customer experience as they are increasingly being used to free humans from their tasks within a customer service center and, although it may seem contradictory, they are helping to provide a more personalized experience. The contribution of this project is the proposal of a cognitive technology model to enhance academic support services with chatbots, which can promote and empower initiatives that facilitate greater use of interaction with the student at Universidad Peruana de Ciencias Aplicadas (UPC).
Tesis

APA, Harvard, Vancouver, ISO, and other styles

11

Kottorp, Max, and Filip Jäderberg. "Chatbot As a Potential Tool for Businesses : A study on chatbots made in collaboration with Bisnode." Thesis, KTH, Industriell ekonomi och organisation (Inst.), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210768.

Full text

Abstract:

The investigation aims to provide an answer to if a chatbot is a potential complement to an internal service desk of a company. The work has centered around developing a chatbot able to handle simple Q&A-interaction of the internal service desk of Bisnode, the company in question. The chatbot acted as an proof of concept, which then was tested by 15 individuals. The testing was done with pre- defined user scenarios, where the test person ultimately had to fill in a questionnaire with statements related to the overall experience. By summarizing the user evaluations from the questionnaires, combined with an SWOT analysis, the work concluded that a chatbot is indeed a potential complement to an internal service desk of a company, if it handles Q&A-interaction.

APA, Harvard, Vancouver, ISO, and other styles

12

Astistova, T. I., and O. B. Typa. "Chatbot development for Telegram social network." Thesis, Київський національний університет технологій та дизайну, 2021. https://er.knutd.edu.ua/handle/123456789/19330.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Dinh, Kevin Hoang. "Chatbot : The future of customer feedback." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-42990.

Full text

Abstract:

This is a study about how to convert a survey to a chatbot and distribute it to various communication channels to collect feedback to improve themselves. What would be the most convenient way to gather feedback? Our daily lives are becoming more and more dependent on digital devices every day. The rise in digital devices leads to a wider range of communication channels. Is it not a good opportunity to use these channels for several purposes. This study focuses on chatbots, survey systems, communication channels, and their ability to gather feedback from respondents and use it to increase the quality of goods, services, and perhaps life. By using chatbot language knowledge, people can engage with the bot in a conversation and answer survey questions in a different way. By using Restful API, the chatbot can extract quantitative information to be analyzed for development. Although the chatbot is not well-made and still requires a lot of adjustments, the work has proven to have many opportunities in surveys, gathering feedback, and analyzing it. This could be an improvement for research regarding chatbots in the future or a new way to make surveys better.
Detta är en studie om hur man konvertera en undersökning till en chattbot och sprida den till olika kommunikationskanaler för att samla återkoppling for att förbättra sig själv. Vad skulle vara det bekvämaste sättet att samla återkoppling? Våra dagliga liv blir mer och mer beroende av digitala enheter var dag. Ökningen av digitala enheter leder till ett större utbud av kommunikationskanaler. Är det inte då en bra möjlighet att utnyttja dessa kanaler för flera ändamål. Det här arbetet focuserar på chattbotar, undersökningssystem och deras förmåga att samla återkoppling från respondenter och använda den för att öka kvaliteten av varor, tjänster och kanske livet. Genom att använda chattbottens språkkunskap kan människor engagera sig med botten i en konversation och svara på undersökningsfrågor på ett annorlunda sätt. Genom att använda sig av något kallat Restful API kan man ta ut kvantitativ information för att analysera den för förbättringssyfte gällande produkter och tjänster. Trots att chattbotten inte är välgjord och fortfarande kräver mycket justeringar så har arbetet visat sig ha många möjligheter inom undersökningar, samla återkoppling och att analysera det. Detta kan vara en förbättring för forskning om chattbottar i framtiden eller ett nytt sätt att förbättra undersökningar.

APA, Harvard, Vancouver, ISO, and other styles

14

Desai, Krutarth. "California State University, San Bernardino Chatbot." CSUSB ScholarWorks, 2018. https://scholarworks.lib.csusb.edu/etd/775.

Full text

Abstract:

Now-a-days the chatbot development has been moving from the field of Artificial-Intelligence labs to the desktops and mobile domain experts. In the fastest growing technology world, most smartphone users spend major time in the messaging apps such as Facebook messenger. A chatbot is a computer program that uses messaging channels to interact with users using natural Languages. Chatbot uses appropriate mapping techniques to transform user inputs into a relational database and fetch the data by calling an existing API and then sends an appropriate response to the user to drive its chats. Drawbacks include the need to learn and use chatbot specific languages such as AIML (Artificial Intelligence Markup Language), high botmaster interference, and the use of non-matured technology. In this project, Facebook messenger based chatbot is proposed to provide domain independent, an easy to use, smart, scalable, dynamic and conversational agent in order to get information about CSUSB. It has the unique functionalities which identify user interactions made by their natural language, and the flawless support of various application domains. This provides an ample of unique scalabilities and abilities that will be evaluated in the future phases of this project.

APA, Harvard, Vancouver, ISO, and other styles

15

Lönnqvist, Izabella, and Filiph Wallsten. "Chatboten Sally : Skillnader i förväntningar och resultat efter införandet av en chatbot hos Helsingborgs kommun." Thesis, Uppsala universitet, Informationssystem, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-376779.

Full text

Abstract:

Chatbotar används idag på en mängd olika sätt. Det är vanligt att chatbotar implementeras som kundservice i olika företag, men att använda sig av en chatbot i en kommun är inte lika förekommande. Chatboten Sally är den första i sitt slag som en servicebot i Helsingborgs kommun och svarar på frågor om Vuxenutbildningen. Denna uppsats är ett resultat av en kvalitativ studie vars syfte har varit att ta reda på vilka förväntningar som fanns på chatboten innan införandet och vad resultat blev. Intervjuerna har gjorts med utvecklarna av chatboten på Helsingborgs kommun, chef samt kommunvägledare på Kontaktcenter. Dessa har haft någon interaktion med chatboten. Studien har identifierat vad som motiverade kommunen till att skapa en chatbot och vad resultat blev, och kunskapsprodukten av den här studien är en genomgång av vad man kan tänka på när man skapar en bot i en kommun.

APA, Harvard, Vancouver, ISO, and other styles

16

Nilstomt, Martin. "Utvärdering av upplevd effektivisering vid användandet av chatbot : Hur upplever supportpersonal chatbotar ur en effektivitetssynpunkt?" Thesis, Karlstads universitet, Handelshögskolan (from 2013), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-73272.

Full text

Abstract:

Detta är en kvalitativ intervjustudie med syfte att undersöka hur supportpersonal upplever chatbotar ur en effektivitetssynpunkt. Fem testdeltagare med erfarenhet av supporthantering intervjuades i studien. Före intervju fick deltagarna genomföra testscenarion med två chatbotar. Testerna genomfördes med data ifrån verkliga och ofta återkommande supportärenden. Därefter intervjuades testdeltagarna om deras upplevelse av effektivisering vid supporthantering med en chatbot. Följande faktorer belystes: tid, kostnad, produktivitet, effektivitet och implementation. Intervjudata antyder att faktorerna är av betydelse för hur supportpersonalen upplever chatbotanvändning ur en effektivitetssynpunkt. Supportpersonalen upplevde att chatbotanvändning skulle kunna medföra både en tidsbesparing och en kostnadseffektivisering. Vidare indikerar intervjudata att en chatbot kan öka supportpersonalens produktivitet liksom effektivitet i supportavdelningen. Resultatet från intervjuerna antyder att implementeringen av en chatbot kan ha en betydelse för såväl tid som kostnad, produktivitet och effektivitet. Detta innebär att hur en implementering genomförs i en verksamhet kan få en inverkan på den sammantagna upplevelsen av effektiviseringen vid chatbotanvändning.

APA, Harvard, Vancouver, ISO, and other styles

17

Arvidsson, Ebba, and Lovisa Kullman. "Chatbot som verktyg inom kundtjänst : Kan en chatbot effektivisera kommunikationen mellan företag och kund vid en orderbeställning?" Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281315.

Full text

Abstract:

Rapporten syftar till att svara på frågan om en chatbot kan effektivisera kommunikationen mellan företag och kund vid en orderbeställning. Arbetet innefattade utvecklandet av en prototyp av en chatbot, med förmågan att hantera specifika ärenden; Boka bud, Våra tjänster, Beräkna pris, Frågor. Chatbottens användbarhet testades senare av 15 testpersoner. I kombination med Think Aloud-metoden utfördes testerna som uppgiftsbaserade scenarion, följt av ett formulär baserat på System Usability Scale (SUS). Medelvärdet av SUS-undersökningen beräknades till 75, vilket antydde att chatbotten är godkänd av användarna, men att det finns utvecklingspotential. Efter analys av resultatet kunde slutsatsen formuleras till att en chatbot kan effektivisera kommunikationen mellan företag och kund vid en orderbeställning. Vid beslutsfattande, om en implementation ska ske eller ej, bör däremot ett flertal faktorer analyseras. Det ska dels finnas ett tydligt syfte med chatbotten och dessutom ska valet av utvecklingsplattform baseras på den unika kravspecifikationen. Utöver dessa faktorer bör även tillgänglig data, fördelar och nackdelar samt andra potentiella lösningar betraktas innan ett beslut tas.
The report aims to provide an answer whether a chatbot can make the communication between companies and customers more effective, when ordering. The work involved development of a prototype of a chatbot, that has the ability to handle specific events; Order a bid, Our services, Calculate the price, Questions. The utility of the chatbot was later tested by 15 individuals. In combination with the Think Aloud-method, the tests were conducted as work-based scenarios followed by a form, based on the System Usability Scale (SUS). The mean value of the SUS-survey was measured to 75, which indicated that the chatbot is approved by the users, but with development potential. After analyzing the result, the conclusion was formulated that a chatbot could make the communication between companies and customers, when ordering. When deciding whether or not an implementation of a chatbot should occur, a number of components should be analyzed. On the other hand, there must be a clear purpose for the chatbot, but also, the choice of which platform that should be implemented must be based on the unique requirements. In addition to these components, available data, advantages and disadvantages as well as potential solutions should be considered before making a final decision.

APA, Harvard, Vancouver, ISO, and other styles

18

Lindblad, Fredrik, and Oskar Andersson. "Chatbot som verktyg för kundtjänst inom larmbranschen." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301953.

Full text

Abstract:

The purpose of the report is to investigate whether a chatbot can both answer the questions that an employee would otherwise have answered and whether it is strategic and financially profitable. The work included the development of a chatbot prototype and an analysis of the economic elements and how well this prototype was considered to function. The chatbot was designed to be able to answer the same type of questions that a new employee is expected to be able to answer with the help of a script, the chatbot also provides the user links to the company’s website in some cases. The background theory in the chatbot is based on machine learning methods (ML) including Natural Language Processing and Neural Networks. Furthermore, methods such as Participant Evaluation and System Usability Scale (SUS) are used to process and analyze the results of the chatbot. Cost Benefit Analysis is the tool used to calculate the economic profitability of a possible implementation. The company Hello Ebbot provided approximate figures on what a final implementation would cost. The average value for the SUS evaluation was 79.2, which can be considered satisfactory, and the breaking point for profitability was that the chatbot needed to process 9.9 % of the calls that could potentially be processed by the chatbot. The participant evaluation showed that the employees at the company were positive in regard of the implementation of the chatbot. The cost of implementing a chatbot does not exceed the cost of a misalignment lasting 6 months. Another positive factor is that the company can be perceived as innovative, which can strengthen their position in the market. In summary, the conclusion was formulated that it is possible to defend an implementation.
Rapporten syftar till att undersöka om en chatbot både kan svara på de frågor som annars en anställd hade svarat på och om den är strategisk samt ekonomisk lönsam. Arbetet i denna rapport innefattade att dels utveckla en prototyop av en chatbot och dels en analys av de ekonomiska elementen och hur väl denna prototyp ansågs fungera. Chatboten konstruerades för att kunna svara på samma typ av frågor som en nyanställd förväntas kunna svara på med hjälp av ett manus, chatboten länkar även till bolagets hemsida i vissa fall. Bakgrundsteorin i chatboten bygger på maskininlärningsmetoder (ML) i egenskap av Naturlig språkbehandling (Eng. Natural Language Processing) och Neurala nätverk. Vidare tas metoder som deltagarutvärdering (Eng. Participant Evaluation) och System Usability Scale (SUS) i anspråk för att bearbeta och analysera resultatet av chatboten. Kostnadsnyttoanalys (Eng. Cost Benefit Analysis) är det verktyg som användes för att beräkna den ekonomiska lönsamheten vid en eventuell implementation. Företaget Hello Ebbot tillhandahöll ungefärliga siffror på vad en slutgilitg implementation skulle innebära kostnadsmässigt. Medelvärdet för SUS-utvärderingen blev 79.2 vilket kan anses tillfredsställande, och brytpunkten för lönsamheten gick vid 9.9% av de samtal som potentiellt kunde behandlas av chatboten. Deltagarutvärderingen påvisade att de anställda på företaget förhöll sig positiva till en implementation av chatboten. Kostnaden för en implementation av en chatbot överstiger inte kostnaden för en mellanställning som varar i 6 månader. En annan positiv faktor är att bolaget kan upplevas som innovativt, vilket kan stärka deras position på marknaden. Sammanfattningsvis formulerades en slutsats att det går att försvara en implementation.

APA, Harvard, Vancouver, ISO, and other styles

19

Strigér, Amanda. "End-to-End Trainable Chatbot for Restaurant Recommendations." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-213982.

Full text

Abstract:

Task-oriented chatbots can be used to automate a specific task, such as finding a restaurant and making a reservation. Implementing such a conversational system can be difficult, requiring domain knowledge and handcrafted rules. The focus of this thesis was to evaluate the possibility of using a neural network-based model to create an end-to-end trainable chatbot that can automate a restaurant reservation service. For this purpose, a sequence-to-sequence model was implemented and trained on dialog data. The strengths and limitations of the system were evaluated and the prediction accuracy of the system was compared against several baselines. With our relatively simple model, we were able to achieve results comparable to the most advanced baseline model. The evaluation has shown some promising strengths of the system but also significant flaws that cannot be overlooked. The current model cannot be used as a standalone system to successfully conduct full conversations with the goal of making a restaurant reservation. The review has, however, contributed with a thorough examination of the current system, and shown where future work ought to be focused.
Chatbotar kan användas för att automatisera enkla uppgifter, som att hitta en restaurang och boka ett bord. Att skapa ett sådant konversationssystem kan dock vara svårt, tidskrävande, och kräva mycket domänkunskap. I denna uppsats undersöks om det är möjligt att använda ett neuralt nätverk för att skapa en chatbot som kan lära sig att automatisera en tjänst som hjälper användaren hitta en restaurang och boka ett bord. För att undersöka detta implementerades en så kallad ``sequence-to-sequence''-modell som sedan tränades på domänspecifik dialogdata. Systemets styrkor och svagheter utvärderades och dess förmåga att generera korrekta svar jämfördes med flera andra modeller. Vår relativt enkla modell uppnådde liknande resultat som den mest avancerade av de andra modellerna. Resultaten visar modellens styrkor, men påvisar även signifikanta brister. Dessa brister gör att systemet, i sig självt, inte kan användas för att skapa en chatbot som kan hjälpa en användare att hitta en passande restaurang. Utvärderingen har dock bidragit med en grundlig undersökning av vilka fel som görs, vilket kan underlätta framtida arbete inom området.

APA, Harvard, Vancouver, ISO, and other styles

20

Östman, Robin, and Marcus Olofsson. "Artificiell Intelligens inom kundtjänst : Med chatbot i centrum." Thesis, Uppsala universitet, Institutionen för informatik och media, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-378911.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Rönnberg, Sofia. "Persuasive Chatbot Conversations : Towards a Personalized User Experience." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166354.

Full text

Abstract:

Helping drivers improve their driving skills and become safer drivers is a problematic topic. Most drivers have a lacking self-assessment ability and consider themselves above average driving skills. This is believed to be related to the lack of continuous feedback after getting the driver’s license. This has led to initiatives to find alternative ways of coaching drivers toward better self-assessment and thereby toward safer driving. Chatbots and conversational interfaces has received increasing attention over the years and could be technologies that can solve these challenges. However, a major challenge to chatbots is that they are mostly implemented in a “one-size-fits-all” approach, and while personalization of the chatbot could solve that challenge, it ishard to achieve. In this study, personalized chatbot conversations that aim to coach drivers are examined. The aim is to create a guide that can help designers and practitioners with design decisions that needs to be considered when creating coaching chatbot conversations. The study was performed as a Wizard of Oz study, where attributes for personalization as well as coaching considerations were tested with users in two iterations to iteratively develop the guide. The findings of the study include the guide itself with its guidelines (see appendix 4), as well as insights on considerations required chatbot personalization and coaching. Regarding personalization, chatbot personality and level of control were identified as two attributes that were fit for adaptation. These can lead to social benefits as well as more tailored services to the users. For coaching, the use of follow-ups, feedback and the chatbot’s attitude are identified as necessary considerations when designing coaching chatbot conversations.

APA, Harvard, Vancouver, ISO, and other styles

22

Hultman, Anna, and Mikaela Zarki. "Do you mind talking to a chatbot? : A quantitative study about how chatbots affect the digital customer experience within Swedish banks." Thesis, Linnéuniversitetet, Institutionen för marknadsföring (MF), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-104863.

Full text

Abstract:

This bachelor's degree thesis aims to increase the understanding of how chatbots affect the digital customer experience within Swedish banks. Furthermore, this study examines how bank chatbot's technical quality affects the digital customer experience. In this thesis, the authors have chosen to use a deductive approach and a quantitative research strategy. Moreover, the authors used the Statistical Package for Social Sciences (SPSS) program to process the collected quantitative data from the questionnaires. The thesis empirical findings were analyzed and discussed in correlation to previous research to strengthen the research results. The thesis empirical findings demonstrate that 42.9% of the respondents agreed with the statement; My bank's chatbot technology quality improved my customer satisfaction. Moreover, the correlation analysis showed that customer satisfaction and customer satisfaction linked to technical quality had a strong positive correlation between the concepts. Swedish banks could use the information to develop further their chatbots' technical quality, which would reduce customer service costs and influence how customers visit the bank. The thesis research results can also be applied and used by other industries that want to improve or implement chatbots in their digital business.

APA, Harvard, Vancouver, ISO, and other styles

23

Richiello, Isabella. "Women's experience of a sexual and reproductive health chatbot." Thesis, KTH, Medieteknik och interaktionsdesign, MID, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231819.

Full text

Abstract:

Chatbots are increasing in popularity and interacting with humans via written language. Previous research has looked at chatbots within several domains, but not towards women’s general sexual and reproductive health. This offers a need to extend the small body of current research. This report aimed to do so by describing women’s experiences of a sexual and reproductive health chatbot used as a decision support tool. The chatbot was designed based on a user-centered approach, allowing women to express desired personality traits in a person when discussing the topic. This resulted in the design creation of two chatbots with two different personalities. Exploratory Wizard of Oz studies were conducted with 6 users by simulating interaction with both chatbots operated by a human. Users were followed up with a survey and interview creating insights to their experiences with each chatbot. Findings resulted in contributing to research with proposed guidelines for how to design a sexual and reproductive health chatbot.
Chatbots blir allt mer populära och interagerar med människor genom skriftligt språk. Tidigare forskning har utforskat olika användningsområden för chatbots, men kvinnors sexuella och reproduktiva hälsa har inte varit en av dessa områden. Detta skapar ett behov att expandera den nuvarande smala forskningen. Denna studie syftar till att göra det genom att beskriva kvinnors erfarenheter av en chatbot för sexuell och reproduktiv hälsa som används som ett beslutsstödsverktyg. Chatboten utformades utifrån ett användarcentrerat tillvägagångssätt, vilket tillät kvinnor att uttrycka önskade personlighetsdrag hos en person som man diskuterar ämnet med. Detta resulterade i ett design skapade av två chatbots med två olika personligheter. Wizard of Oz studier genomfördes med 6 användare genom att simulera interaktionen med båda chatbots drivna av en människa. Deltagarna följdes upp med en enkät, följt av en intervju för bättre insikt till deras erfarenhet med varje chatbot. Resultaten resulterade i att bidra till forskning med förslag på riktlinjer för hur man utformar en chatbot för sexuell och reproduktiv hälsa.

APA, Harvard, Vancouver, ISO, and other styles

24

Abu, Shawar Bayan Aref. "A corpus based approach to generalising a chatbot system." Thesis, University of Leeds, 2005. http://etheses.whiterose.ac.uk/1323/.

Full text

Abstract:

Chatbot tools are computer programs which interact with users using natural languages. Most developers built their systems aiming to fool users that they are talking with real humans. Up to now most chatbots serve as a tool to amuse users through chatting with a robot. However, the knowledge bases of almost all chatbots are edited manually which restricts users to specific languages and domains. This thesis shows that chatbot technology could be used in many different ways in addition to being a tool for fun. A chatbot could be used as a tool to learn or study a new language, a tool to access an information system, a tool to visualise the contents of a corpus and a tool to give answers to questions in a specific domain. Instead of being restricted to a specific domain or written language, a chatbot could be trained with any text in any language. Some of the differences between real human conversations and human-chatbot dialogues are presented. A Java program has been developed to read a text from a machine readaatbble text (corpus) and convert it to ALICE chatbot format language (AIML). The program was built to be general, the generality in this respect implies no restrictions on specific language, domain or structure. Different languages were tested: English, Arabic, Afrikaans, French and Spanish. At the same time different corpora structures were used: dialogue, monologue and structured text.

APA, Harvard, Vancouver, ISO, and other styles

25

Fredriksson, Joakim, and Falk Höppner. "Chatbot for Information Retrieval from Unstructured Natural Language Documents." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-40532.

Full text

Abstract:

This thesis brings forward the development of a chatbot which retrieves information from a data source consisting of unstructured natural language text. This project was made in collaboration with the company Jayway in Halmstad. Elasticsearch was used to create the search function and the service Dialogflow was used to process the natural language input from the user. A Python script was created to retrieve the information from the data source, and a request handler was written which connected the tools together to create a working chatbot. The chatbot correctly answers questions with a accuracy of 72% according to testing with a sample of n = 25. The testing consisted of asking the chatbot questions and determining if the answer is correct. Possible further research could be done to explore how chatbots might help the elderly or people with disabilities use the web with a natural dialogue instead of a traditional user interface.

APA, Harvard, Vancouver, ISO, and other styles

26

Nagarajan, Santhosh Kumar. "Server-Less Rule-Based Chatbot Using Deep Neural Network." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-395931.

Full text

Abstract:

Customer support entails multi-faceted benefits for IT businesses. Presently, the business depends upon on conventional channels like e-mail, customer care and web interface to provide customer support services. However, with the advent of new developments in Scania IT, different IT business units is driving a shift towards automated chatbot solutions to provide flexible responses to the user's questions. This thesis presents a practical study of such chatbot solution for the company SCANIA CV AB, Södertälje. The objective of the research work presented in this thesis is to analyze several deep learning approaches in order to develop a chatbot prototype using serverless Amazon Web Services components. The proposed bot prototype includes two main Natural Language Understanding (NLU) tasks: Intent classification and Intent fulfilment. This is a two-step process, focusing first on Recurrent Neural Network (RNN) to perform a sentence classification (intent detection task). Then, a slot filling mechanism is used for intent fulfilment task for the extraction of parameters. The results from several neural network structures for user intent classification are analyzed and compared. It is found that the bidirectional Gated Recurrent units (GRU) were shown to be the most effective for the classification task. The concluded model is then deployed on the designed AWS stack. They demonstrate that the bot behaves as expected and it places more insistence on the structure of the neural network and word embeddings for future advancements in order to find an even better neural network structure.

APA, Harvard, Vancouver, ISO, and other styles

27

Ihs, Håkansson Ellinor. "Hur kan en chatbot implementeras som ett hjälpmedel för supporttekniker? : En förstudie för att undersöka möjligheten att implementera en chatbot i en industriell verksamhet." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-159637.

Full text

Abstract:

Syftet med det projekt som beskriv i denna uppsats är att undersökta möjligheterna med att implementera en chatbot i Siemens verksamhet. Fokuset för chatboten skulle vara att den på något sätt skulle implementeras som ett hjälpmedel för supportteknikerna på Siemens. Supportteknikerna arbetar dygnet runt med kundärenden som kommer in rörande deras maskiner. Därmed behöver supportteknikerna ibland hitta dokumentation och information kring dessa maskiner för att kunna ge rekommendationer till kund om hur det eventuella problemet ska lösas. I denna studie gjordes en litteraturundersökning kring chatbotar i allmänhet, tekniken kring chatbotar idag och hur en chatbot bör designas. Dessutom genomfördes en datainsamling i form av kontextuella intervjuer som sedan strukturerades till ett affinitetsdiagram. Detta affinitetsdiagram var i sin tur grunden för den persona och det kontextscenario som skapades. Affinitetsdiagrammet och de kontextuella intervjuerna beskrivs i mer detalj i arbetet skrivet av Linn Olsson (2019). Utifrån personan, kontextscenariot, affinitetsdiagrammet samt bakgrundslitteraturen skapades en uppsättning krav. Dessa var krav kring hur chatboten skulle se ut och fungera. Det som eftersöktes mest var något som kopplade samman alla system de använde sig av för att hitta information kring de olika maskinerna, samt en enklare sökfunktion för att hitta specifik dokumentation kring ett visst taggnamn. Kraven blev sedan poängsatta och prioriterade av supporttekniker på Siemens. De prioriterade kraven var utgångspunkten i designandet av en prototyp av en chatbot. Detta implementerades sedan i en interaktiv prototyp. Den prototyp som skapades är ett första utkast på hur en chatbot skulle kunna se ut för just uppgiften att hitta specifik information. Denna uppgift var som tidigare nämnts något de uttryckte sig vara i störst behov av. Detta förslag på användningsområde för en chatbot i Siemens system hade troligtvis underlättat supportteknikernas arbete i ganska stor grad. Det minskar tiden de lägger på att försöka hitta informationen så att de snabbare kan lösa kundärenden. Det här visar på att det finns möjligheter att implementera en chatbot i deras system. Dock krävs ytterligare undersökningar kring exakt vad för information supportteknikerna vill åt, samt hur det ska möjliggöras att de kan få tag på denna information, för att kunna implementera en chatbot. Dessutom skulle de behöva undersöka fler uppgifter som denna chatbot skulle vara användningsbar för. Detta för att chatboten får ett större användningsområde och kan på så vis få en större avgränsning från att likna en begränsad sökmotor. På så vis skulle detta vara ytterligare argument för att en chatbot bör implementeras.

APA, Harvard, Vancouver, ISO, and other styles

28

Björnhed, Joakim. "Using a Chatbot to Prevent Identity Fraud By Social Engineering." Thesis, University of Skövde, School of Humanities and Informatics, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-3396.

Full text

Abstract:

Social engineering is a threat that is expanding and threatens organisations existence. A social engineer can get hold of crucial business information that is vital for the organisation and by this threaten the organisation. To prevent successful fraud attempts the organisations need to educate their employees about social engineering fraud techniques that can be used for gaining information. Hence, information security education needs new educational approaches to cope with the threats.

A solution to the problem is the use of an automated chatbot that gives the employees knowledge about a threat that is difficult to spot. To understand if an automated chatbot is a possible solution to educate the users, an investigation about the applicability is conducted. The investigation is based on a survey that compares traditional security education that is based on reading a written informational text and the use of an automated chatbot that simulates a fraud attempt with the purpose to steal an identity. The education with the automated chatbot is to be exposed to an identity fraud attempt in a controlled environment and then get an explanation of what have happened and way.

The automated chatbot is developed with a fraud attempt that looks like a normal market research approach, the market research where conducted with question that gather information that is important for identity thefts.

The result of the investigation shows that it may be possible to use an automated chatbot for educating in social engineering fraud attacks. However there is still a need to solve several major problems before there are possible to make sure the concept is fully feasible.

APA, Harvard, Vancouver, ISO, and other styles

29

Abdul-Kader, Sameera A'amer. "An investigation on question answering for an online feedable Chatbot." Thesis, University of Essex, 2018. http://repository.essex.ac.uk/23345/.

Full text

Abstract:

This thesis presents the design and implementation of a Chatbot that is able to answer questions about an entity it is learning about. This Chatbot is capable of automatically generating multiple genres using a unique technique to populate its SQL database from the Web. Our Online Feedable Chatbot can hold a conversation with the user regarding the information it has extracted from the Web. Our Online Feedable Chatbot attempts to create Question Answer pairs (QAPs) and acquire imperative sentences specially targeted at the entity it gives information about. A method to select the best response for a Chatbot query among a set of sentences using hybrid terms, syntactic, and semantic extracted features is developed as a response search system of our Online Feedable Chatbot. This tutor Chatbot can expand its training knowledge base by automatically extracting more QAPs and imperative sentences from the Web whenever the user needs to learn about a new entity and without any instructor's supervision, amendments, or control.

APA, Harvard, Vancouver, ISO, and other styles

30

Westman, Gunnar, and Michael Hjälmö. "En undersökning av möjligheten att anpassa en chatbot för mailkonversationer." Thesis, KTH, Hälsoinformatik och logistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-278064.

Full text

Abstract:

Sammanfattning Utgångspunkten för detta examensarbete är att bestämma hur väl en chatbot kan anpassas förmailkonversationer. Om chatbotar kan anpassas för mailkonversationer skulle behovet avmänskligt arbete vid monotona och förutsägbara mailkonversationer kunna minskas.Examensarbetet har implementerat ett existerande chatbot-ramverk och utvecklat ettdialogbeslutssystem för svarskonstruktion utifrån de klassificerade avsikterna. Hela systemetkallas för konversationsenhet. Målet för konversationsenheten är att uppnå ettprecisionsvärde på 0,90, som uppnåddes med en implementation av Watson assistant.Precisionsvärdet används för att mäta hur väl konversationsenheten kan anpassas förmailkonversationer. Dialogbeslutssystemet ska kunna ge olika svar beroende på vilkaavsikter som är klassificerade och svar som beror på förekomsten av andra avsikter ska varaoberoende av ordningen avsikterna blev klassificerade. Det utvecklade dialogbeslutssystemetuppnåde de uppsatta målen. Nyckelord Chatbot, NLU, Mailbot, Dialogbeslutssystem
AbstractThe starting point for this thesis is to determine how well a chatbot can be adapted for emailconversations. If chatbots can be customized for email conversations, the need for humanwork in monotonous and predictable email conversations could be reduced. An existingchatbot framework has been implemented and a dialogue decision system for responseconstruction based on the classified intents has been developed. The whole system is called aconversational unit. The goal of the conversation unit is to achieve a precision value of 0.90,which was achieved with an implementation of Watson assistant. The precision value is usedto measure how well the conversation unit can be adapted for mail conversations. Thedialogue decision system should be able to give different answers depending on what intentsare classified and answers that depend on the existence of other intents should be independentof the order the intents were classified. The developed dialogue decision system achieves theset goals.KeywordsChatbot, NLU, Mailbot, Dialog decision system4

APA, Harvard, Vancouver, ISO, and other styles

31

Samakovlis, Niki, and Adam Särnell. "En tematisk analys av Skatteverkets chatbot utifrån den statliga värdegrunden." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-298267.

Full text

Abstract:

Som statligt anställd på en svensk myndighet ska ens arbete genomsyras av demokratiska värderingar enligt den statliga värdegrunden. Skatteverket har sedan 2018 använt sig av en digital medarbetare i form av chatboten Skatti som svarar på vanliga frågor om folkbokföring och inkomstdeklarationer. I dagsläget är användandet av artificiell intelligens och chatbotar inte vanligt förekommande hos svenska statliga myndigheter. Därför är det av intresse att undersöka vilka områden som borde tas hänsyn till utifrån den statliga värdegrunden när myndigheter väljer att implementera chatbotar i deras verksamhet. För att undersöka detta har 15562 st meddelanden till chatboten Skatti från besökare på Skatteverkets hemsida analyserats genom metoden tematisk analys. Under metodens gång identifierades 184 st koder som resulterade i 14 st teman vilka beskriver den undersökta datan. Dessa teman användes sedan för att diskutera huruvida Skatti utvecklats med den statliga värdegrunden i åtanke. Studiens resultat indikerar att det existerar områden där Skatti på olika sätt inte följer den statliga värdegrunden till fullo och att det kan vara av intresse att ta hänsyn till dessa i den framtida utvecklingen av Skatti.
As a government employee at a Swedish authority, one’s work must be permeated by democratic values according to the public service ethos. Since 2018, the Swedish Tax Agency has used a digital employee: a chatbot called Skatti which answers common questions about national registration and income tax returns. At present, the use of artificial intelligence and chatbots is not common among Swedish public services. Therefore it is of interest to investigate which areas should be taken into account based on the public service ethos when authorities choose to implement chatbots in their operations. To investigate this, 15562 messages sent to the chatbot Skatti from visitors to the Swedish Tax Agency’s website were analyzed using thematic analysis. During the course of the analysis, 184 codes were identified which resulted in 15 themes describing the examined data. These themes were later used to discuss whether Skatti had been developed with the public service ethos in mind. The results of the study indicate that there are areas where Skatti in various ways does not fully follow the public service ethos and that it may be of interest to take these areas into account in the future development of Skatti.

APA, Harvard, Vancouver, ISO, and other styles

32

Burri, Ramón. "Improving user trust towards conversational chatbot interfaces with voice output." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-240585.

Full text

Abstract:

This thesis investigates the impact of the voice modality on user trust in conversational chatbot interfaces. The assumption is that trust can be increased by adding voice output to a chatbot and by a higher quality of a used text-to-speech synthesis. The thesis first introduces chatbots and the concept of conversational interfaces then defines trust in an online context. Based on this, a model for trust and perceiving factors for credibility, ease of use and risk is defined. An online experiment is conducted where participants run through conversational scenarios with a chatbot while varying the voice output. Followed by a survey to collect data about the perception of the trust factors for a scenario with no voice and two scenarios with different speech synthesis qualities. To analyse the ordinal data from the survey the ”Wilcoxon signed- rank test”, a nonparametric statistical test, is conducted to compare trust for the voice output types. Results show that adding the voice output modality to a conversational chatbot interface increases the user trust towards the service. Furthermore, the assumption that synthesis quality has an effect on trust could not hold true because the results are not statistically significant. On this basis, the limitations of the used methods are discussed and suggestions for further research are proposed.
Detta examensarbete undersöker den inverkan som röstmodaliteten har på användarförtroende i konversationsbaserade gränssnitt för chatbottar. Antagandet är att förtroendet kan ökas, dels genom att addera röstutmatning till chatbotten och dels genom att text-till-röst-syntesen ges hög kvalité. Först introduceras chatbottar och konceptet konversationsbaserade gränssnitt. Därefter definieras örtroende i en online-kontext. Baserat på detta definieras en modell för förtroende samt uppfattningsfaktorer för trovärdighet, lättanvändhet och risk. Ett onlineexperiment utfördes, där deltagare går igenom konversationscenarion med en chatbot medan röstutmatningen varieras. Därefter följde en undersökning ämnad att samla in data om uppfattningen om förtroendefaktorerna för ett scenario utan röst och två scenarion med olika talsyntes-kvalitéer. För att analysera den ordnade datan från undersökningen genomfördes Wilcoxon signedrank-testet, ett ickeparametriskt statistiskt test, för att jämföra förtroenden för de olika röstutmatningstyperna. Resultaten visar att addering av röstutmatningsmodalitet till ett konversationsbaserat chatbotsgränsnitt ökar användares förtroende för tjänsten. Vidare, antagandet att synteskvalitén har effekt på förtroendet kunde inte verifieras därför att resultaten inte är statistiskt signifikanta. Begränsningarna hos de använda metoderna diskuteras och förslag för framtida forskning läggs fram.

APA, Harvard, Vancouver, ISO, and other styles

33

Gardner, Angelica. "Improving the Chatbot Experience : With a Content-based Recommender System." Thesis, Mittuniversitetet, Institutionen för informationssystem och –teknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-36306.

Full text

Abstract:

Chatbots are computer programs with the capability to lead a conversation with a human user. When a chatbot is unable to match a user’s utterance to any predefined answer, it will use a fallback intent; a generic response that does not contribute to the conversation in any meaningful way. This report aims to investigate if a content-based recommender system could provide support to a chatbot agent in case of these fallback experiences. Content-based recommender systems use content to filter, prioritize and deliver relevant information to users. Their purpose is to search through a large amount of content and predict recommendations based on user requirements. The recommender system developed in this project consists of four components: a web spider, a Bag-of-words model, a graph database, and the GraphQL API. The anticipation was to capture web page articles and rank them with a numeric scoring to figure out which articles that make for the best recommendation concerning given subjects. The chatbot agent could then use these recommended articles to provide the user with value and help instead of a generic response. After the evaluation, it was found that the recommender system in principle fulfilled all requirements, but that the scoring algorithm used could achieve significant improvements in its recommendations if a more advanced algorithm would be implemented. The scoring algorithm used in this project is based on word count, which lacks taking the context of the dialogue between the user and the agent into consideration, among other things.

APA, Harvard, Vancouver, ISO, and other styles

34

Vilela, Tiago André Pimpão. "Global Mobility Chatbot: Chatbot model to improve mobile employee experience." Master's thesis, 2021. http://hdl.handle.net/10362/116183.

Full text

Abstract:

Dissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Marketing Intelligence
The Global Mobility Industry is the area that comprehends the emerging internationalization and growth of companies outside borders. Its overall core essence is to support businesses all over the world in setting up operations, by assigning employees in other cities or countries outside the company's headquarters. These operations have intrinsically a set of challenges and opportunities that both companies and employees need to face while on move. To face these challenges and accomplish international move tasks and goals, software houses have been developing over the past years platforms and solutions to face each of the international moves phases. However, it's hard to keep every task, request, event, and everything on track and both accomplishing and managing it can become a struggle when the number of employees on assignment multiplies and grows year after year. The usage of Chatbots is not new in the tech world, but the technology, features, and capabilities of those have been growing and growing, and those are gaining a significant space and importance in a variety of different businesses and social fields, such as sales, real state, eCommerce, customer support, and even marketing and enterprise bots. Its capacity to work as a true virtual assistant, able to respond and support users 24/7, it’s becoming something more and more desirable for every company and employee. This dissertation has the goal to, first, make a deeper research and study on the Global Mobility Industry and the Chatbot usage and development. Defining and stating how helpful and valuable a chatbot could be when integrated with a Global Mobility software solution. By concluding this study, 2 built artifacts will result from it, specifically a backlog full of business requirements to accomplish, and a prototype of the chatbot using one of the top Chatbot enablers platforms in the market. To work and develop the artifacts, this dissertation will follow the design science research methodology, whose evaluation phase will be supported by a user testing session and a structured interview with carefully selected participants, with pre-defined closed and open-ended questions. Everything resulting from this dissertation will leave open space for future enhancements, by incrementing the value and functionalities of the chatbot, and potential real-world application and integration of it in Global Mobility softwares and platforms.

APA, Harvard, Vancouver, ISO, and other styles

35

Lino, Pedro Manuel Dias Braga. "Travel Booking Chatbot." Master's thesis, 2018. https://repositorio-aberto.up.pt/handle/10216/114378.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Ferreira, Tiago Miguel Moreira. "Chatbot Automóvel Adaptável." Master's thesis, 2017. https://repositorio-aberto.up.pt/handle/10216/106510.

Full text

Abstract:

Com o crescente número de objetos do dia-a-dia que contêm uma ligação à Internet sendo capazes de enviar e receber dados, a chamada \textit{Internet of Things} (IoT) -- a necessidade de ter sistemas que interajam com esses mesmos objetos também cresceu. Esta necessidade cresceu tanto que nesta altura muitos dos fabricantes destes objetos já distribuem software desenhado para interagir com os seus produtos. No entanto, isto requer que o utilizador instale uma aplicação diferente para cada produto que queira utilizar e que, na maior parte das vezes, seja obrigado a navegar por interfaces e menus complicados para realizar uma simples tarefa.O advento de \textit{chatbots} provou ser um digno tópico de estudo e desenvolvimento, com a aceitação por parte do publico alvo como uma substituição relativamente a aplicações móveis \textit{standard}, sendo uma das principais razões o facto de bots poderem ser usados nas suas aplicações de troca de mensagens preferidas. A maior parte dos \textit{bots} existentes atualmente no mercado, apenas respondem a input especifico por parte do utilizador; no entanto, com os avanços recentes nas áreas de Inteligência Artificial e Processamento de Linguagem Natural, esta abordagem tem sido alterada para uma conversacional, servindo como uma maneira de envolver o utilizador no produto. Este conceito foi provado através da criação de assistentes pessoais por grandes empresas como a Google ou Apple.Esta dissertação tem como objetivo criar um \textit{chatbot} que extenda a relação do utilizador com o seu carro, permitindo que este realize operações que tenham em conta a sua localização, verificar o estado do seu carro e realizar operações sobre este, apenas falando com o \textit{bot}. Por exemplo, o utilizador pode localizar onde é que o carro está estacionado, realizar ações baseadas na sua localização, ou até ser notificado quando existe algum problema mecânico com mensagens do tipo O sistema da transmissão avariou, deveria visitar um mecânico''. Isto é obtido através da transmissão de dados a partir do carro com um adaptador OBD-II com ligação 4G permanente para um servidor aplicacional. O servidor recebe input do utilizador que é processado usado sistemas atuais de processamento de linguagem natural \textit{as a service}, tal como o Amazon Lex. O bot aprende com o utilizador modelando as suas viagens através do modelo estatístico ARIMA.Para avaliar este trabalho, a aplicação foi testada com testes de usabilidade quer internamente quer externamente, onde no fim, os participantes convidados a fazer uma avaliação da sua experiência através de um questionário. O reconhecimento de padrões e previsões foram também testados com dados reais.
With the increasing number of everyday objects having an Internet connection and being able to send and receive data, the so called IoT (Internet of Things) -- the need to have systems that interact with such objects has also grown. This need has grown so much that at this time most manufacturers already ship software designed to interact with their products. However, this typically requires the user to install a separate application for each product and, most of the times, to navigate through complicated menus just to perform some simple tasks.The advent of chat bots has proven to be a worthy topic of research and development, with general acceptance from the target audiences, who view them as a replacement to standard mobile applications, one of the reasons being that bots can be used in their favorite messaging application. Most of the bots available in the market respond only to specific user input; however, with the recent advances in Artificial Intelligence and Natural Language Processing, this approach is being shifted towards engaging conversations with the users, serving as a way to engage the user with the product. This has been proven with the creation of personal assistants by some big companies like Google or Apple.This dissertation aims to create a chat bot that extends the relationship of the users with their cars, allowing a user to easily make location-aware operations, check the car current status and perform operations on the car just by talking with the bot. For instance, the user can locate where the car is parked or even get notified when there is a problem with the mechanical system of the car. This is done by sending the car data through an OBD-II dongle with permanent 4G connectivity to an application server. The server receives user input that is processed using state of the art natural language processing systems as a service such as Amazon Lex, and sends commands back to the car if necessary. The bot learns user patterns by modeling past trips using the ARIMA statistical model. This being a bot that must be able to be used while driving using voice to communicate, raises some challenges mainly on how to interact and direct the conversational flow, understanding the differences between texting and talking, along with accurately and at the right time make proactive suggestions to the user.To evaluate this work, the application was tested with usability tests both internally and externally, where at the end, the participants were asked to fill a questionnaire regarding their experience. The pattern recognition and predictions were also tested against real data.

APA, Harvard, Vancouver, ISO, and other styles

37

Chang, Chiung-Chih, and 張瓊之. "Style-Changeable Chatbot." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/m2zn5m.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Lino, Pedro Manuel Dias Braga. "Travel Booking Chatbot." Dissertação, 2018. https://repositorio-aberto.up.pt/handle/10216/114378.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Ferreira, Tiago Miguel Moreira. "Chatbot Automóvel Adaptável." Dissertação, 2017. https://repositorio-aberto.up.pt/handle/10216/106510.

Full text

Abstract:

Com o crescente número de objetos do dia-a-dia que contêm uma ligação à Internet sendo capazes de enviar e receber dados, a chamada \textit{Internet of Things} (IoT) -- a necessidade de ter sistemas que interajam com esses mesmos objetos também cresceu. Esta necessidade cresceu tanto que nesta altura muitos dos fabricantes destes objetos já distribuem software desenhado para interagir com os seus produtos. No entanto, isto requer que o utilizador instale uma aplicação diferente para cada produto que queira utilizar e que, na maior parte das vezes, seja obrigado a navegar por interfaces e menus complicados para realizar uma simples tarefa.O advento de \textit{chatbots} provou ser um digno tópico de estudo e desenvolvimento, com a aceitação por parte do publico alvo como uma substituição relativamente a aplicações móveis \textit{standard}, sendo uma das principais razões o facto de bots poderem ser usados nas suas aplicações de troca de mensagens preferidas. A maior parte dos \textit{bots} existentes atualmente no mercado, apenas respondem a input especifico por parte do utilizador; no entanto, com os avanços recentes nas áreas de Inteligência Artificial e Processamento de Linguagem Natural, esta abordagem tem sido alterada para uma conversacional, servindo como uma maneira de envolver o utilizador no produto. Este conceito foi provado através da criação de assistentes pessoais por grandes empresas como a Google ou Apple.Esta dissertação tem como objetivo criar um \textit{chatbot} que extenda a relação do utilizador com o seu carro, permitindo que este realize operações que tenham em conta a sua localização, verificar o estado do seu carro e realizar operações sobre este, apenas falando com o \textit{bot}. Por exemplo, o utilizador pode localizar onde é que o carro está estacionado, realizar ações baseadas na sua localização, ou até ser notificado quando existe algum problema mecânico com mensagens do tipo O sistema da transmissão avariou, deveria visitar um mecânico''. Isto é obtido através da transmissão de dados a partir do carro com um adaptador OBD-II com ligação 4G permanente para um servidor aplicacional. O servidor recebe input do utilizador que é processado usado sistemas atuais de processamento de linguagem natural \textit{as a service}, tal como o Amazon Lex. O bot aprende com o utilizador modelando as suas viagens através do modelo estatístico ARIMA.Para avaliar este trabalho, a aplicação foi testada com testes de usabilidade quer internamente quer externamente, onde no fim, os participantes convidados a fazer uma avaliação da sua experiência através de um questionário. O reconhecimento de padrões e previsões foram também testados com dados reais.
With the increasing number of everyday objects having an Internet connection and being able to send and receive data, the so called IoT (Internet of Things) -- the need to have systems that interact with such objects has also grown. This need has grown so much that at this time most manufacturers already ship software designed to interact with their products. However, this typically requires the user to install a separate application for each product and, most of the times, to navigate through complicated menus just to perform some simple tasks.The advent of chat bots has proven to be a worthy topic of research and development, with general acceptance from the target audiences, who view them as a replacement to standard mobile applications, one of the reasons being that bots can be used in their favorite messaging application. Most of the bots available in the market respond only to specific user input; however, with the recent advances in Artificial Intelligence and Natural Language Processing, this approach is being shifted towards engaging conversations with the users, serving as a way to engage the user with the product. This has been proven with the creation of personal assistants by some big companies like Google or Apple.This dissertation aims to create a chat bot that extends the relationship of the users with their cars, allowing a user to easily make location-aware operations, check the car current status and perform operations on the car just by talking with the bot. For instance, the user can locate where the car is parked or even get notified when there is a problem with the mechanical system of the car. This is done by sending the car data through an OBD-II dongle with permanent 4G connectivity to an application server. The server receives user input that is processed using state of the art natural language processing systems as a service such as Amazon Lex, and sends commands back to the car if necessary. The bot learns user patterns by modeling past trips using the ARIMA statistical model. This being a bot that must be able to be used while driving using voice to communicate, raises some challenges mainly on how to interact and direct the conversational flow, understanding the differences between texting and talking, along with accurately and at the right time make proactive suggestions to the user.To evaluate this work, the application was tested with usability tests both internally and externally, where at the end, the participants were asked to fill a questionnaire regarding their experience. The pattern recognition and predictions were also tested against real data.

APA, Harvard, Vancouver, ISO, and other styles

40

Huang, Pei-Ju, and 黃珮茹. "Chatbot commerce－An empirical analysis of chatbot usage scenarios and user intentions." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/bny92b.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Gonçalez, Fernando Feliu. "Chatbot para atendimento automatizado." Master's thesis, 2021. http://hdl.handle.net/10284/9946.

Full text

Abstract:

A área da inteligência artificial vem evoluindo muito rapidamente junto com as tecnologias computacionais. O desenvolvimento de máquinas capazes de realizar tarefas, que até então eram exclusivamente humanas, como atendimento de clientes, por exemplo, tem se tornado cada vez mais comum. Deste modo o chatbot é uma tecnologia que vem revolucionando a maneira que as empresas estão prestando seus serviços, permitindo a redução de custos com pessoal, padronização das informações e uma melhor experiencia com o seu usuário final. Entre as diversas aplicações está o atendimento ao cliente, onde o mesmo pode obter informações, esclarecer dúvidas e até mesmo realizar operações de maneira autónoma, prática e com alta qualidade. O presente trabalho apresenta um estudo e desenvolvimento de um chatbot como mais uma alternativa ao atendimento padrão já realizado hoje dentro de uma central de atendimento.

APA, Harvard, Vancouver, ISO, and other styles

42

Barradas, Nuno Alexandre Mestre. "A book-oriented chatbot." Master's thesis, 2020. http://hdl.handle.net/10071/22099.

Full text

Abstract:

The automatic answer to questions in natural language is an area that has been studied for many years. However, based on the existing question answering systems, the percentage of correct answers over a set of questions, generated from a dataset, we can see that the performance it is still far away from to 100%, which is many times the value achieved when the questions are tested by humans. This work addresses the idea of a book-oriented Chatbot, more precisely a question answering system directed to answer to questions in which the dataset is one or more books. This way, we intend to adopt a new system, incorporating two existent projects, the OpenBookQA and the Question-Generation. We have used two Domain Specific Datasets that were not studied in both project, that were the QA4MRE and RACE. To these we have applied the main approach: enrich them with automatic generated questions. We have run many experiments, training neural network models. This way, we intended to study the impact of those questions and obtain good accuracy results for both datasets. The obtained results suggest that having a significant representation of generated questions in a dataset, leads to a higher test accuracy results of correct answers. Becoming clear that, enrich a dataset, based on a book, with generated questions about that book, is giving to the dataset the content of the book. This dissertation presents promising results, through the datasets with automatic generated questions.
A resposta automática a perguntas em língua natural é um tema estudado há largos anos. Tendo por base os sistemas existentes de resposta a perguntas, quando comparamos a percentagem de respostas correctas sobre um conjunto de perguntas, geradas a partir de um conjunto de dados, conseguimos ver que o desempenho está ainda longe de 100%, que muitas vezes é o valor alcançado quando as perguntas são testadas por humanos. Este trabalho aborda a ideia de um agente conversacional orientado para livros, mais propriamente um sistema de resposta a perguntas direccionado para responder a perguntas cujo conjunto de dados seja um ou mais livros. Deste modo, pretendemos adoptar um novo sistema, incorporando dois projectos existentes, o OpenBookQA e o Question-Generation. Utilizámos dois conjuntos de dados de domínio específico, sem terem sido ainda estudados nos dois projectos, que foram o QA4MRE e o RACE. A estes aplicámos a abordagem principal: enriquecê-los com perguntas geradas automaticamente. Corremos uma série de experiências, treinando modelos de redes neuronais. Deste modo, pretendemos estudar o impacto das perguntas geradas e obter bons resultados de precisão de respostas correctas para os dois conjuntos de dados. Os resultados obtidos sugerem que ter uma quantidade significativa de perguntas geradas num conjunto de dados, conduz a maior precisão de respostas correctas. Tornando claro que, enriquecer um dataset, sobre um livro, com perguntas geradas sobre esse mesmo livro, é dar ao dataset o contéudo do livro. Esta dissertação apresenta resultados promissores, a partir de conjuntos de dados com perguntas geradas automaticamente.

APA, Harvard, Vancouver, ISO, and other styles

43

Teixeira, Fábio André Alves. "Chatbot para serviços bancários." Master's thesis, 2018. https://hdl.handle.net/10216/118800.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Jakúbek, Tomáš. "Chatbot k aplikácii MojiLidi." Master's thesis, 2019. http://www.nusl.cz/ntk/nusl-429093.

Full text

Abstract:

This diploma thesis deals with building a chatbot for the MojiLidi system, which helps to find specialists and companies providing their services and products. Chatbot is a type of interface that is controlled by a natural language conversation. Thus, users do not need to know the meaning of buttons or forms and for them it is enough just to say request. The work describes the main parts of chatbot such as understanding the natural language, managing the dialogue, creating responses, communication channel and the conversational user interface. Consequently, such a conversation agent is created and integrated into the MojiLidi web interface from where it helps users in 4 domains.

APA, Harvard, Vancouver, ISO, and other styles

45

Ho, Ching-Ting, and 何靖霆. "Flow-based Chatbot Framework." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/g4am4u.

Full text

Abstract:

碩士
國立臺灣海洋大學
資訊工程學系
105
Nowadays, more and more ChatBotChatbots are dependent built onon those social platforms like Facebook, line, and slack. Accordingly growing day by day, but also more and moremany tools and online platforms for building ChatBotChatbots have been constructed and widely usedappeared one after another., However, these tools or platforms are not able to fully support the control of chat flow, the management of conversations, and bi-directional Web service integration. but they usually focus on a single function. If a userwe want plans to build a ChatBotChatbot with complex chat flows, an ability of integrating Web APIs, and a capability of that has NLP (Natural Language Processing) analysis、external service expansion and simple dialogue management features, the user must to write complex conversation scripts and even a lot of additional codesintegrate other services, which caused difficulties in building; It causes the development and maintenance difficult and costly.. Therefore, to address the above issues, we propose a novel approach, referred to as FCF (Fflow-based Chatbot Fframework). that FCF was developed built on the Node-Red platform. It not only to provide builders can quickly build a business ChatBot, but also to to provide a visual and flow-based construction interface environment for Chatbot design. FCF allows Chatbot developers to quickly build Chatbots for business contexts in a visualized wayand flow-oriented concept to reduce the difficulty of building. We FCF also relies on theuse Api.ai APIs to support NLP analysis and the newly-deviseddevelop a service concatenation datastandard format for service webhook to support NLPallow bidirectional and external service extensionsintegration. For the feature of the service module expansion, In addition, to realize “Flow as a Service (FaaS)”, wwe also set up a n online platform ChatBotChatbot Market for Chatbot developers builders to share publish and access find established the chat flows. At the end of the studyFor the experiments, we preparedused a transaction “buy smartphones” example to be as a testbed to compare FCF with two existing ChatBotChatbot building tools, Api.ai and Red Bot. ,E xperiment results demonstrate that FCF outperforms these tools in terms of reduced complexity of development and maintenanceto explain our framework have the advantage of operation and efficiency.

APA, Harvard, Vancouver, ISO, and other styles

46

Teixeira, Fábio André Alves. "Chatbot para serviços bancários." Dissertação, 2018. https://hdl.handle.net/10216/118800.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Baptista, Bruno Miguel Costa. "IPBRICK OS - AI Voice/Chatbot." Master's thesis, 2022. https://hdl.handle.net/10216/140739.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Pereira, Nuno Filipe Reininho Proença. "Chatbot na Área de Sistemas Financeiros." Master's thesis, 2019. https://hdl.handle.net/10216/119703.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Carvalho, João Rafael da Silva. "Chatbot para ajuda de novos alunos." Master's thesis, 2020. http://hdl.handle.net/10348/10722.

Full text

Abstract:

Dissertação submetida à UNIVERSIDADE DE TRÁS-OS-MONTES E ALTO DOURO para obtenção do grau de MESTRE em Engenharia Electrotécnica e de Computadores
Na Universidade de Trás-os-Montes e Alto Douro (UTAD), no início de cada ano letivo, existe um aumento do tempo de resposta dos serviços da universidade porque, os funcionários desses serviços, apesar de capazes, sofrem uma enorme sobrecarga no seu trabalho. A principal razão é a grande afluência de alunos recém-chegados de diversas origens. Por isso, para ser possível responder ao crescente aumento de alunos, aliviando os funcionários de perguntas de caráter mais simples, surgiu a necessidade de criar um sistema autónomo de respostas. Desta forma, para simular a intervenção humana o melhor possível foi desenvolvido um chatbot, que funciona na plataforma Facebook Messenger capaz de conversar em duas línguas, português e inglês. Como caso de estudo, foram postas em prática técnicas de Processamento de Linguagem Natural e Machine learning, nas quais se aplicam redes neuronais para a classificação da frase recebida e extração de uma intenção. A extração de uma intenção permite selecionar a resposta adequada para a frase recebida. Implementaram-se, no total, seis redes neuronais para cada língua, e, por sua vez, cada rede neuronal foi treinada num conjunto de dados diferente, correspondente a um serviço da universidade. Testaram-se os valores da precisão e os valores da função de perda de todos os modelos criados. De seguida, considerando vários parâmetros das redes neuronais fixos, alterou-se a função de ativação no neurónio de forma a encontrar a solução mais vantajosa, desta forma, utilizaram-se duas funções de ativação diferentes: a função de ativação de tangente hiperbólica e ReLU. Destes testes, conclui-se que, nos dados relativos à língua portuguesa, a função que apresentou melhor desempenho foi a função ReLU, na qual a precisão mínima obtida nos dados de validação foi de 96%. Enquanto que nos dados relativos à língua inglesa, a função tangente hiperbólica apresentou melhor desempenho nos dados de validação, com uma precisão mínima obtida de 88%
In the Universidade de Tr´as-os-Montes e Alto Douro, in the beggining of each school year, there is an increase in the time of response from the main services of the university because, the employees of these services, although capable, suffer a huge overload in their work. The main reason of this is the great influx of students from diverse origins. Because of this, in order to respond to the growing number of students without a significant increase in staff, a need has arisen to create an autonomous system to answer more simple questions. Thus, to simulate human intervention as best as possible, a chatbot has been developed, which works on the Facebook Messenger platform capable of chatting in two languages, Portuguese and English. As a case of study, are implemented techniques from Natural Language Processing and Machine learning, where neural networks are applied for phrase classification and intention extraction. The extraction of the intent allows to select the right response for the received phrase. A total of 6 neural networks were implemented for each language, where each neural network was trained on a different data set, each corresponding to a different service of the university. Considering several fixed parameters, the activation function in the neurons was changed in order to find a better solution, thus, two activation functions were used, hyperbolic tangent and ReLU. From these tests it can be concluded that in the Portuguese data, the function that presented the best performance was the ReLU function, where the minimum precision value obtained in the validation dataset was 96 %, while in the English data, the tanh function presented the best performance, with a minimum accuracy value in the validation dataset of 88 %.

APA, Harvard, Vancouver, ISO, and other styles

50

Pereira, Nuno Filipe Reininho Proença. "Chatbot na Área de Sistemas Financeiros." Dissertação, 2019. https://hdl.handle.net/10216/119703.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Dissertations / Theses on the topic 'Chatbot'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles