Academic literature on the topic 'Learning Analytics (LA)'

The prevalence of big data has rapidly changed the usage and mechanisms of data analytics within organizations. Big data is a widely-used term without a clear definition. The difference between big data and traditional data can be characterized by four Vs: velocity (speed at which data is generated), volume (amount of data generated), variety (the data can take on different forms), and veracity (the data may be of poor/unknown quality). As many industries begin to recognize the value of big data, organizations try to capture it through means such as: side-channel data in a manufacturing operation, unstructured text-data reported by healthcare personnel, various demographic information of households from census surveys, and the range of communication data that define communities and social networks. Big data analytics generally follows this framework: first, a digitized process generates a stream of data, this raw data stream is pre-processed to convert the data into a usable format, the pre-processed data is analyzed using statistical tools. In this stage, called statistical learning of the data, analysts have two main objectives (1) develop a statistical model that captures the behavior of the process from a sample of the data (2) identify anomalies in the process. However, several open challenges still exist in this framework for big data analytics. Recently, data types such as free-text data are also being captured. Although many established processing techniques exist for other data types, free-text data comes from a wide range of individuals and is subject to syntax, grammar, language, and colloquialisms that require substantially different processing approaches. Once the data is processed, open challenges still exist in the statistical learning step of understanding the data. Statistical learning aims to satisfy two objectives, (1) develop a model that highlights general patterns in the data (2) create a signaling mechanism to identify if outliers are present in the data. Statistical modeling is widely utilized as researchers have created a variety of statistical models to explain everyday phenomena such as predicting energy usage behavior, traffic patterns, and stock market behaviors, among others. However, new applications of big data with increasingly varied designs present interesting challenges. Consider the example of free-text analysis posed above. There's a renewed interest in modeling free-text narratives from sources such as online reviews, customer complaints, or patient safety event reports, into intuitive themes or topics. As previously mentioned, documents describing the same phenomena can vary widely in their word usage and structure. Another recent interest area of statistical learning is using the environmental conditions that people live, work, and grow in, to infer their quality of life. It is well established that social factors play a role in overall health outcomes, however, clinical applications of these social determinants of health is a recent and an open problem. These examples are just a few of many examples wherein new applications of big data pose complex challenges requiring thoughtful and inventive approaches to processing, analyzing, and modeling data. Although a large body of research exists in the area of anomaly detection increasingly complicated data sources (such as side-channel related data or network-based data) present equally convoluted challenges. For effective anomaly-detection, analysts define parameters and rules, so that when large collections of raw data are aggregated, pieces of data that do not conform are easily noticed and flagged In this work, I investigate the different steps of the data analytics framework and propose improvements for each step, paired with practical applications, to demonstrate the efficacy of my methods. This paper focuses on the healthcare, manufacturing and social-networking industries, but the materials are broad enough to have wide applications across data analytics generally. My main contributions can be summarized as follows: • In the big data analytics framework, raw data initially goes through a pre-processing step. Although many pre-processing techniques exist, there are several challenges in pre-processing text data and I develop a pre-processing tool for text data. • In the next step of the data analytics framework, there are challenges in both statistical modeling and anomaly detection o I address the research area of statistical modeling in two ways: -There are open challenges in defining models to characterize text data. I introduce a community extraction model that autonomously aggregates text documents into intuitive communities/groups -In health care, it is well established that social factors play a role in overall health outcomes however developing a statistical model that characterizes these relationships is an open research area. I developed statistical models for generalizing relationships between social determinants of health of a cohort and general medical risk factors o I address the research area of anomaly detection in two ways: -A variety of anomaly detection techniques exist already, however, some of these methods lack a rigorous statistical investigation thereby making them ineffective to a practitioner. I identify critical shortcomings to a proposed network based anomaly detection technique and introduce methodological improvements -Manufacturing enterprises which are now more connected than ever are vulnerably to anomalies in the form of cyber-physical attacks. I developed a sensor-based side-channel technique for anomaly detection in a manufacturing process<br>PHD<br>The prevalence of big data has rapidly changed the usage and mechanisms of data analytics within organizations. The fields of manufacturing and healthcare are two examples of industries that are currently undergoing significant transformations due to the rise of big data. The addition of large sensory systems is changing how parts are being manufactured and inspected and the prevalence of Health Information Technology (HIT) systems in healthcare systems is also changing the way healthcare services are delivered. These industries are turning to big data analytics in the hopes of acquiring many of the benefits other sectors are experiencing, including reducing cost, improving safety, and boosting productivity. However, there are many challenges that exist along with the framework of big data analytics, from pre-processing raw data, to statistical modeling of the data, and identifying anomalies present in the data or process. This work offers significant contributions in each of the aforementioned areas and includes practical real-world applications. Big data analytics generally follows this framework: first, a digitized process generates a stream of data, this raw data stream is pre-processed to convert the data into a usable format, the pre-processed data is analyzed using statistical tools. In this stage, called ‘statistical learning of the data’, analysts have two main objectives (1) develop a statistical model that captures the behavior of the process from a sample of the data (2) identify anomalies or outliers in the process. In this work, I investigate the different steps of the data analytics framework and propose improvements for each step, paired with practical applications, to demonstrate the efficacy of my methods. This work focuses on the healthcare and manufacturing industries, but the materials are broad enough to have wide applications across data analytics generally. My main contributions can be summarized as follows: In the big data analytics framework, raw data initially goes through a pre-processing step. Although many pre-processing techniques exist, there are several challenges in pre-processing text data and I develop a pre-processing tool for text data. In the next step of the data analytics framework, there are challenges in both statistical modeling and anomaly detection I address the research area of statistical modeling in two ways: There are open challenges in defining models to characterize text data. I introduce a community extraction model that autonomously aggregates text documents into intuitive communities/groups In health care, it is well established that social factors play a role in overall health outcomes however developing a statistical model that characterizes these relationships is an open research area. I developed statistical models for generalizing relationships between social determinants of health of a cohort and general medical risk factors o I address the research area of anomaly detection in two ways: A variety of anomaly detection techniques exist already, however, some of these methods lack a rigorous statistical investigation thereby making them ineffective to a practitioner. I identify critical shortcomings to a proposed network-based anomaly detection technique and introduce methodological improvements Manufacturing enterprises which are now more connected than ever are vulnerable to anomalies in the form of cyber-physical attacks. I developed a sensor-based side-channel technique for anomaly detection in a manufacturing process.

Research has provided relevant advances in evidence-based design for productive learning. For example, in the field of collaborative learning, there is extensive evidence for some key learning design elements, such as methods of structuring activity sequencing, group formation techniques, and technology mediating collaboration. However, progress has been more limited in the area of evidence-based design of collaborative learning physical spaces. Contradictorily, research on learning spaces and their impact on teaching and learning have been a field of inquiry for decades. Existing studies have explored how learning spaces can play a role in inhibiting or encouraging student participation in active learning tasks, such those applying collaborative learning methods. However, the methods used in these studies have provided limited empirical evidence on the effects that specific design elements of collaborative learning spaces have on student behaviour. In this context, technological advances in data capture and analysis tools offer new opportunities and challenges to overcome this lack of evidence. In particular, the potential to advance learning space research through approaches involving Multimodal Learning Analytics (MMLA) is becoming increasingly clear. This dissertation contributes to emerging MMLA research by aiming to disentangle the effects of space design elements and their interaction with other learning design elements in order to help broaden the evidence-based design spectrum with more fruitful learning. In particular, the thesis focuses on the interaction of table shapes in learning spaces with the group size learning design element. The dissertation also explores the relevant, but often neglected, gender perspective. An experimental design methodology is applied with the objective of answering research questions related to: (1) the differences in student behaviour when two table shapes and two group sizes are used; (2) indicators relevant to collaborative learning space research; and (3) data collection, analytical, and visualisation techniques. Contributions include the first empirical evidence about the influence of table shape on student behaviour, including effects arising from the interaction of table shape with group size and student gender. In addition, the dissertation offers a new case that discusses MMLA indicators in this field and explores how motion capture, temporal analysis, and aggregated visualisation can contribute to collaborative learning space research.<br>Ha habido avances importantes en la investigación en el ámbito del diseño para el aprendizaje efectivo basado en evidencias. Por ejemplo, en el ámbito del aprendizaje colaborativo, se han conseguido evidencias sobre algunos elementos importantes de su diseño, como los métodos para estructurar las secuencias de actividades, las técnicas de formación de grupo o la tecnología que media la colaboración. Sin embargo, el avance ha sido más limitado en el área del diseño de los espacios físicos para el aprendizaje colaborativo. Contradictoriamente, la investigación sobre los espacios de aprendizaje y su impacto en la educación han sido objeto de investigación durante décadas. Estudios existentes han explorado cómo los espacios de aprendizaje juegan un papel en inhibir o favorecer la participación de los estudiantes en tareas de aprendizaje activo, como las que aplican métodos de aprendizaje colaborativo. Sin embargo, los métodos utilizados en estos estudios han generado muy pocas evidencias empíricas sobre los efectos que elementos específicos de esos espacios tienen en el comportamiento de los estudiantes. En este contexto, los avances en las tecnologías para la captura y el análisis de datos ofrecen nuevas oportunidades, y retos, para cubrir esta falta de evidencias. En particular, el potencial de la Analítica de Aprendizaje Multimodal (MMLA, de sus siglas en inglés) se está vislumbrando como especialmente prometedor para avanzar la investigación sobre los espacios de aprendizaje. Esta tesis doctoral contribuye al campo emergente de MMLA con el objetivo de desgranar los efectos de los elementos de diseño en los espacios de aprendizaje y su interacción con otros elementos de diseño para el aprendizaje. El objetivo último es ampliar el espectro del diseño basado en evidencias para el aprendizaje efectivo. Para ello, la tesis se centra en estudiar la interacción de las formas de las mesas con el tamaño de grupo, como elementos de diseño sobre el espacio y sobre el método de aprendizaje. La tesis también explora la perspectiva de género, una perspectiva relevante pero no suficientemente considerada en el ámbito. La metodología empleada es de diseño experimental y se plantean preguntas de investigación relacionadas con: (1) las diferencias en el comportamiento de los estudiantes cuando se utilizan dos tipos de mesas y tamaños de grupo; (2) los indicadores de analítica de aprendizaje relevantes en la investigación de espacios de aprendizaje colaborativo; (3) las técnicas para la recogida, el análisis y la visualización de datos. Las contribuciones de la tesis incluyen unas primeras evidencias científicas sobre la influencia de las formas de las mesas en el comportamiento de los estudiantes, considerando la interacción con el tamaño de grupo y el género. Además, la tesis también ofrece un nuevo caso de recogida de datos que permite revisar la validez de indicadores MMLA propuestos en el campo y explorar como aproximaciones de captura de movimiento, análisis temporal y visualización avanzada pueden contribuir a la investigación en espacios para el aprendizaje colaborativo.

Der Einsatz digitaler Medien hat in der nationalen Hochschullehre Tradition. Lernmanagementsysteme (LMS), E-Learning, Blended Learning, etc. sind Schlagwörter im Hochschulalltag. Allerdings stellt sich die Frage, was LMS und Blended Learning im Zeitalter digitaler Vernetzung und der herangewachsenen Generation der “Digital Natives” leisten (können bzw. sollen)? Die Verbreitung neuer Technologien im Zusammenhang mit neuen Lehr- und Lernkonzepten wie OER, MOOCS, etc. macht zudem die Entwicklung von Analytics-Instrumenten erforderlich. Das ist auch im nationalen Diskurs von großem Interesse und legt neue Handlungsfelder für Hochschulen offen. Doch es stellt sich die Frage, warum Learning Analytics (LA) bzw. Academic Analytics (AA) bisher nur in einem geringfügigen Maße an deutschen Hochschulen erfolgreich zum Einsatz kommen und warum eine Nutzung insbesondere in LMS, wie zum Beispiel OPAL, nicht ohne Weiteres realisierbar erscheint. Hierzu sollen Einflussfaktoren, die die Implementierung von LA- und AA-Instrumenten hemmen, identifiziert und diskutiert werden. Aufbauend darauf werden erste Handlungsfelder vorgestellt, deren Beachtung eine verstärkte Einbettung von LA- und AA Instrumenten in LMS möglich machen soll.

Forecasting is a powerful tool that can enable companies to save millions in revenue every year if the forecast is good enough. The problem lies in the good enough part. Many companies today use Excel topredict their future sales and trends. While this is a start it is far from optimal. Seco Analytics aim to solve this issue by forecasting in an informative and easy manner. The web application uses the ARIMA analysis method to accurately calculate the trend given any country and product area selection. It also features external data that allow the user to compare internal data with relevant external data such as GDP and calculate the correlation given the countries and product areas selected. This thesis describes the developing process of the application Seco Analytics.

Thesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, System Design and Management Program, 2017.<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 113-115).<br>Learning Analytics (LA) is defined as the collection, measurement, and analysis of data related to student performance such that the feedback from the analytical insights can be used to optimize student learning and improve student outcomes. Blended Learning (BL) is a teaching paradigm that involves a mix of face-to-face interactions in a classroom based setting along with instructional material distributed through an online medium. In this thesis, we explore the role of a blended learning model coupled with learning analytics in an introductory programming class for non-computer science students. We identify the features that were necessary for setting up the infrastructure of the course. These include discussions on preparing the course content materials and producing assignment exercises. We then talk about the various dynamics that were in play during the duration of the class by describing the interplay between watching video tutorials, listening to mini-lectures and performing active learning exercises that are backed by modern software development practices. Lastly, we spend time analyzing the data collected to create a predictive model that can measure student performance by defining the specifications of a machine learning algorithm along with many of its adjustable parameters. The system thus created will allow instructors to identify possible outliers in teaching efficacy, the feedback from which could then be used to tune course material for the betterment of student outcomes.<br>by Anuj Bheda.<br>S.M. in Engineering and Management

The ubiquitous use of computers and greater accessibility of the Internet have triggered widespread use of educational innovations such as online discussion forums, Wikis, Open Educational Resources, MOOCs, to name a few. These advances have led to the creation of a wide range of instructional videos, written documents and discussion archives by engineering learners seeking to expand their learning and advance their knowledge beyond the engineering classroom. However, it remains a challenging task to assess the quality of knowledge advancement on these learning platforms particularly due to the informal nature of engagement as a whole and the massive amount of learner-generated data. This research addresses this broad challenge through a research approach based on the examination of the state of knowledge advancement, analysis of relationships between variables indicative of knowledge creation and participation in knowledge creation, and identification of groups of learners. The study site is an online engineering community, All About Circuits, that serves 31,219 electrical and electronics engineering learners who contributed 503,908 messages in 65,209 topics. The knowledge creation metaphor provides the guiding theoretical framework for this research. This metaphor is based on a set of related theories that conceptualizes learning as a collaborative process of developing shared knowledge artifacts for the collective benefit of a community of learners. In a knowledge-creating community, the quality of learning and participation can be evaluated by examining the degree of collaboration and the advancement of knowledge artifacts over an extended period of time. Software routines were written in Python programming language to collect and process more than half a million messages, and to extract user-produced data from 87,263 web pages to examine the use of engineering terms, social networks and engineering artifacts. Descriptive analysis found that state of knowledge advancement varies across discussion topics and the level of engagement in knowledge creating activities varies across individuals. Non-parametric correlation analysis uncovered strong associations between topic length and knowledge creating activities, and between the total interactions experienced by individuals and individual engagement in knowledge creating activities. On the other hand, the variable of individual total membership period has week associations with individual engagement in knowledge creating activities. K-means clustering analysis identified the presence of eight clusters of individuals with varying lengths of participation and membership, and Kruskal-Wallis tests confirmed that significant differences between the clusters. Based on a comparative analysis of Kruskal-Wallis Score Means and the examination of descriptive statistics for each cluster, three groups of learners were identified: Disengaged (88% of all individuals), Transient (10%) and Engaged (2%). A comparison of Spearman Correlations between pairs of variables suggests that variable of individual active membership period exhibits stronger association with knowledge creation activities for the group of Disengaged, whereas the variable of individual total interactions exhibits stronger association with knowledge creation activities for the group of Engaged. Limitations of the study are discussed and recommendations for future work are made.<br>Ph. D.

The numerous surveillance videos recorded by a single stationary wide-angle-view camera persuade the use of a moving point as the representation of each small-size object in wide video scene. The sequence of the positions of each moving point can be used to generate a trajectory containing both spatial and temporal information of object's movement. In this study, we investigate how the relationship between two trajectories can be used to recognize multi-agent interactions. For this purpose, we present a simple set of qualitative atomic disjoint trajectory-segment relations which can be utilized to represent the relationships between two trajectories. Given a pair of adjacent concurrent trajectories, we segment the trajectory pair to get the ordered sequence of related trajectory-segments. Each pair of corresponding trajectory-segments then is assigned a token associated with the trajectory-segment relation, which leads to the generation of a string called a pairwise trajectory-segment relationship sequence. From a group of pairwise trajectory-segment relationship sequences, we utilize an unsupervised learning algorithm, particularly the k-medians clustering, to detect interesting patterns that can be used to classify lower-level multi-agent activities. We evaluate the effectiveness of the proposed approach by comparing the activity classes predicted by our method to the actual classes from the ground-truth set obtained using the crowdsourcing technique. The results show that the relationships between a pair of trajectories can signify the low-level multi-agent activities.