Academic literature on the topic 'Les messages texte (SMS)'

AbstractWe address the problem of unsupervised and semi-supervised SMS (Short Message Service) text message SPAM detection. We develop a content-based Bayesian classification approach which is a modest extension of the technique discussed by Resnik and Hardisty in 2010. The approach assumes that the bodies of the SMS messages arise from a probabilistic generative model and estimates the model parameters by Gibbs sampling using an unlabeled, or partially labeled, SMS training message corpus. The approach classifies new SMS messages as SPAM or HAM (non-SPAM) by zero-thresholding their logit estimates. We tested the approach on a publicly available SMS corpora collected from the UK. Used in semi-supervised fashion, the approach clearly outperformed a competing algorithm, Semi-Boost. Used in unsupervised fashion, the approach outperformed a fully supervised classifier, an SVM (Support Vector Machine), when the number of training messages used by the SVM was small and performed comparably otherwise. We believe the approach works well and is a useful tool for SMS SPAM detection.

Over a three-month period (spanning 15 September to 15 December 2011), over 90,000 authentic text messages in French were collected by a group of academics in the Languedoc-Roussillon region of France. This paper retraces the organisation of the data collection, the elaboration of the sociolinguistic questionnaire that donors were invited to fill out, text message data processing procedures and preliminary results. A shift from individual “isolated” text messages to “conversational” SMS exchanges is then studied, in preparation for a new SMS conversational data collection which is due to take place in the near future. This whole process is important for understanding in-depth interactional practices within contemporary digital textuality and should provide insight for pluri-disciplinary approaches.

Background SMS text messaging is a low-cost and far-reaching modality that can be used to augment existing diabetes prevention programs and improve long-term diet and exercise behavior change adherence. To date, little research has been published regarding the process of SMS text message content development. Understanding how interventions are developed is necessary to evaluate their evidence base and to guide the implementation of effective and scalable mobile health interventions in public health initiatives and in future research. Objective This study aims to describe the development and refinement of a bank of SMS text messages targeting diet and exercise behavior change to be implemented following a diabetes prevention program. Methods A bank of 124 theory-based SMS text messages was developed using the Behaviour Change Wheel and linked to active intervention components (behavior change techniques [BCTs]). The Behaviour Change Wheel is a theory-based framework that provides structure to intervention development and can guide the use of evidence-based practices in behavior change interventions. Once the messages were written, 18 individuals who either participated in a diabetes prevention program or were a diabetes prevention coach evaluated the messages on their clarity, utility, and relevance via survey using a 5-point Likert scale. Messages were refined according to participant feedback and recoded to obtain an accurate representation of BCTs in the final bank. Results 76/124 (61.3%) messages were edited, 4/124 (3.2%) were added, and 8/124 (6.5%) were removed based on participant scores and feedback. Of the edited messages, 43/76 (57%) received minor word choice and grammar alterations while retaining their original BCT code; the remaining 43% (33/76, plus the 4 newly written messages) were recoded by a reviewer trained in BCT identification. Conclusions This study outlines the process used to develop and refine a bank of SMS text messages to be implemented following a diabetes prevention program. This resulted in a bank of 120 theory-based, user-informed SMS text messages that were overall deemed clear, useful, and relevant by both individuals who will be receiving and delivering them. This formative development process can be used as a blueprint in future SMS text messaging development to ensure that message content is representative of the evidence base and is also grounded in theory and evaluated by key knowledge users.

SMS spam detection is an important task where spam SMS messages are identified and filtered. As greater numbers of SMS messages are communicated every day, it is very difficult for a user to remember and correlate the newer SMS messages received in context to previously received SMS. SMS threads provide a solution to this problem. In this work the problem of SMS spam detection and thread identification is discussed and a state of the art clustering-based algorithm is presented. The work is planned in two stages. In the first stage the binary classification technique is applied to categorize SMS messages into two categories namely, spam and non-spam SMS; then, in the second stage, SMS clusters are created for non-spam SMS messages using non-negative matrix factorization and K-means clustering techniques. A threading-based similarity feature, that is, time between consecutive communications, is described for the identification of SMS threads, and the impact of the time threshold in thread identification is also analysed experimentally. Performance parameters like accuracy, precision, recall and F-measure are also evaluated. The SMS threads identified in this proposed work can be used in applications like SMS thread summarization, SMS folder classification and other SMS management-related tasks.

Objective: The objective of this study is to identify features and content that short message service (SMS) should have in order to motivate HIV testing among men who have sex with men (MSM) in Lima, Peru. Methods: From October, 2010 to February, 2011, we conducted focus groups at two stages; six focus groups were conducted to explore and identify SMS content and features and two additional focus groups were conducted to tailor SMS content. The text messages were elaborated within the theoretical framework of the Information-Motivation-Behavioral Skills model and the Social Support Theory. Results: A total of 62 individuals participated in the focus groups. The mean age of participants was 28 years (range 18-39). We identified important features and content items needed for the successful delivery of text messages, including: a) the use of neutral and coded language; b) appropriate frequency and time of delivery; c) avoiding mass and repetitive messages; and d) use of short, concise and creative messages. Although in Peru receiving text messages is usually a free service, it is important to remind participants that receiving messages will be free of charge. Conclusion: Text messages can be used to promote HIV testing among Peruvian MSM. It is important to consider adequate frequency, message content and cost when delivering messages to promote HIV testing in this population.

AbstractObjectiveThe aim of the study was to verify the effectiveness of short text messages (short message service, or SMS) as an additional notification tool in case of fire or a mass casualty incident in a hospital.MethodsA total of 2242 SMS text messages were sent to 59 hospital workers divided into 3 groups (n=21, n=19, n=19). Messages were sent from a Samsung GT-S8500 Wave cell phone and Orange Poland was chosen as the telecommunication provider. During a 3-month trial period, messages were sent between 3:35 PM and midnight with no regular pattern. Employees were asked to respond by telling how much time it would take them to reach the hospital in case of a mass casualty incident.ResultsThe mean reaction time (SMS reply) was 36.41 minutes. The mean declared time of arrival to the hospital was 100.5 minutes. After excluding 10% of extreme values for declared arrival time, the mean arrival time was estimated as 38.35 minutes.ConclusionsShort text messages (SMS) can be considered an additional tool for notifying medical staff in case of a mass casualty incident. (Disaster Med Public Health Preparedness. 2016;10:38–41)

A majority of the world’s population now live in areas with a mobile telephone network. This expansion of the network enables people to use more mobile phone functionalities such as short message service, multimedia, and the Internet. Mobile phone–based health (mHealth) interventions have been considered to have benefits in low-income countries. The aim of this study was to explore the feasibility of a short message service for breastfeeding education in Ethiopia. Four focus groups—two with mothers and two with fathers—were conducted with a total of 41 participants. The focus group discussion recordings were transcribed in Tigrigna verbatim, and then translated to English. The data were analyzed using thematic analysis, underpinned by the technology acceptance model. The following four general themes emerged from the focus group discussions: (1) Mobile phones: integrated into everyday life; (2) SMS text messaging: anytime, anywhere, as long as there is a sound; (3) Marketing versus utility: a barrier to SMS; and (4) Scientific messages from credible experts are key to reading SMS-based messages. Parents in Ethiopia showed interest in receiving weekly infant feeding-related short messages. Short message service–based interventions could therefore be an option for improving knowledge and awareness of parents regarding infant feeding.

AbstractElectronic written texts used in computer-mediated interactions (emails, blogs, chats, and the like) contain significant deviations from the norm of the language. This paper presents the detail of a system aiming at normalizing the orthography of French SMS messages: after discussing the linguistic peculiarities of these messages and possible approaches to their automatic normalization, we present, compare, and evaluate various instanciations of a normalization device based on weighted finite-state transducers. These experiments show that using an intermediate phonemic representation and training, our system outperforms an alternative normalization system based on phrase-based statistical machine translation techniques.

Background: HIV poses a threat to global health. With effective treatment options available, education and testing strategies are essential in preventing transmission. Text messaging is an effective tool for health promotion and can be used to target higher risk populations. This study reports on the design, delivery and testing of a mobile text messaging SMS intervention for HIV prevention and awareness, aimed at adults in the construction industry and delivered during the COVID-19 pandemic. Method: Participants were recruited at Test@Work workplace health promotion events (21 sites, n = 464 employees), including health checks with HIV testing. Message development was based on a participatory design and included a focus group (n = 9) and message fidelity testing (n = 291) with assessment of intervention uptake, reach, acceptability, and engagement. Barriers to HIV testing were identified and mapped to the COM-B behavioural model. 23 one-way push SMS messages (19 included short web links) were generated and fidelity tested, then sent via automated SMS to two employee cohorts over a 10-week period during the COVID-19 pandemic. Engagement metrics measured were: opt-outs, SMS delivered/read, number of clicks per web link, four two-way pull messages exploring repeat HIV testing, learning new information, perceived usefulness and behaviour change. Results: 291 people participated (68.3% of eligible attendees). A total of 7726 messages were sent between March and June 2020, with 91.6% successfully delivered (100% read). 12.4% of participants opted out over 10 weeks. Of delivered messages, links were clicked an average of 14.4% times, max 24.1% for HIV related links. The number of clicks on web links declined over time (r = −6.24, p = 0.01). Response rate for two-way pull messages was 13.7% of participants. Since the workplace HIV test offer at recruitment, 21.6% reported having taken a further HIV test. Qualitative replies indicated behavioural influence of messaging on exercise, lifestyle behaviours and intention to HIV test. Conclusions: SMS messaging for HIV prevention and awareness is acceptable to adults in the construction industry, has high uptake, low attrition and good engagement with message content, when delivered during a global pandemic. Data collection methods may need refinement for audience, and effect of COVID-19 on results is yet to be understood.

Background Atherosclerotic cardiovascular disease (ASCVD) is the leading cause of mortality worldwide, with a prevalence of approximately 100 million patients. There is evidence that antiplatelet agents and antihypertensive medications could reduce the risk of new vascular events in this population; however, treatment adherence is very low. An SMS text messaging intervention was recently developed based on behavior change techniques to increase adherence to pharmacological treatment among patients with a history of ASCVD. Objective This study aims to evaluate the efficacy and safety of an SMS text messaging intervention to improve adherence to cardiovascular medications in patients with ASCVD. Methods A randomized controlled clinical trial for patients with a prior diagnosis of cardiovascular events, such as acute myocardial infarction, unstable angina, cerebrovascular disease, or peripheral artery disease, in one center in Colombia was conducted. Patients randomized to the intervention arm were assigned to receive SMS text messages daily for the first 4 weeks, 5 SMS text messages on week 5, 3 SMS text messages each in weeks 6 and 7, and 1 SMS text message weekly from week 8 until week 52. In contrast, patients in the control arm received a monthly SMS text message reminding them of the next study appointment and the importance of the study, requesting information about changes in their phone number, and thanking them for participating in the study. The primary endpoint was the change in low-density lipoprotein cholesterol (LDL-C) levels, whereas the secondary endpoints were the changes in thromboxane B2 levels, heart rate, systolic and diastolic blood pressure, medication adherence, cardiac and noncardiac mortality, and hospitalization. Linear regression analyses and bivariate tests were performed. Results Of the 930 randomized patients, 805 (86.5%) completed follow-up and were analyzed for the primary endpoint. There was no evidence that the intervention changed the primary outcome (LDL-C levels; P=.41) or any of the secondary outcomes evaluated (all P>.05). There was also no evidence that the intervention was associated with adverse events. Conclusions In this study, there was no evidence that a behavior modification intervention delivered by SMS text messaging improved LDL-C levels, blood pressure levels, or adherence at 12 months. More research is needed to evaluate whether different SMS text messaging strategies, including personalized messages and different timings, are effective; future studies should include mixed methods to better understand why, for whom, and in which context (eg, health system or social environment) SMS text messaging interventions work (or not) to improve adherence in patients with ASCVD. Trial Registration ClinicalTrials.gov NCT03098186; https://clinicaltrials.gov/ct2/show/NCT03098186 International Registered Report Identifier (IRRID) RR2-10.1136/bmjopen-2018-028017