Using Machine Learning to Establish the Concerns of Persons with HIV/AIDS During the COVID-19 Pandemic from their Tweets

There are millions of People Living with HIV/AIDS (PLWHA) globally and over the years, addressing their concerns has been topical for many stakeholders. It is a well-known and established fact that PLWHA are at increased risk of victimization and stigmatization. Unfortunately, the world experienced an outbreak of the COVID-19 pandemic that has led to strict social measures in many states. Thus, it is the goal of this research to study the impact that the outbreak and its mitigation measures have had on the PLWHA. Specifically, we sought to highlight their concerns from sentiments expressed on social media based on posted tweets. By combining machine learning (ML) techniques such as textual mining and thematic analysis, we determined 14 major themes as factors that are worth exploring. In this work, we originally extracted 2,839,091 tweets related to HIV/AIDS posted from March 2020 to April 2022. After initially doing data cleaning and preprocessing, we performed topic modeling using the Latent Dirichlet Allocation (LDA) topic model to extract 25 topics that are made up of 30 keywords each. The topics were then narrowed into 14 themes. The paper details the negative, positive, and neutral sentiment polarities which we highlight as concerning. These sentiments were determined using the Valence Aware Dictionary and sEntiment Reasoner (VADER) Sentiment Analysis Library with a 90% F1-score compared to TextBlob which showed a 53% F1-score. The research findings highlight issues affecting PLWHA during and post-pandemic such as high cost of medical care, late diagnosis of HIV, limited access to medications, stigmatization and victimization, absence of testing kits in hospitals, and lack of urgency in the development of vaccines or cure for HIV. Author

Sociodemographic Differences in the Utilization of Remote Pulmonary Artery Pressure Measurements for Heart Failure Patients in the USA

Background The COVID-19 pandemic prompted a major surge in telehealth practices, including the increased utilization of remote Pulmonary Artery Pressure (PAP) among cardiologists worldwide. This study aimed to assess the sociodemographic differences in the utilization of the CardioMEMS HF system for remote PAP monitoring in patients with Heart Failure in the USA. Methods The National inpatient sample database of the USA was queried for all patients with HF who received the CardioMEMS HF system between 2016 and 2019. Multiple logistic regression models were subsequently performed to investigate the socio-demographic factors influencing remote pulmonary artery pressure measurements. Results A total of 1540 patients had a CardioMEMS device for remote PAP monitoring between 2016 and 2019. Following a multivariate analysis accounting for potential confounders, we noted that the use of remote PAP was lower in women vs. men (Adjusted odds ratio (AOR): 0.65, CI 0.52 - 0.82, p < 0.001). Patients who lived in low (AOR: 0.38, CI 0.25 - 0.57, p < 0.001), medium (AOR: 0.57, CI 0.40 - 0.82, p = 0.003), and high-income neighborhoods (AOR: 0.60, CI 0.44 - 0.82, p < 0.001), were also less likely to have remote PAP compared to patients who lived in very high-income neighborhoods. There was no racial difference or association between device use and primary insurance payer. Conclusion There are inequities in the utilization of remote PAP monitoring amongst the Heart Failure population within the USA.Copyright © 2023 American College of Cardiology Foundation

TidyHome: A Persuasive App for Supporting Victims and Survivors of Domestic Violence

Domestic violence is a prevalent issue affecting women worldwide. This issue has been intensified by the COVID-19 pandemic. While several measures have been attempted to address domestic violence, the use of technology has been shown to provide support for victims when planning for their safety. In this paper, we designed a persuasive mobile app, called TidyHome, targeted at women ages 15–49 years who are victims or survivors of domestic or intimate partner violence. The app addresses the issue of domestic violence with the aim of promoting safety behavior and safety consciousness in victims and survivors of domestic violence. To achieve this, we followed a user-centered design approach. Specifically, we obtained user preferences by conducting focus group sessions to gather ideas and opinions on features to be implemented in the app. We then designed low-fidelity prototypes (LFP) illustrating various features of TidyHome based on our findings from the focus group. Thereafter, we conducted a user study evaluating the LFP and assessing the perceived persuasiveness of the features illustrated in the LFP. Based on the results obtained from the LFP evaluation, we designed high-fidelity prototypes (HFP) reflecting only the features perceived as significantly persuasive. Finally, we conducted an evaluation of the HFP assessing its usability, and refined the HFP based on qualitative feedback after thematic analysis. Our results indicate that 8 features of the app were considered persuasive and very relevant for supporting female victims of domestic violence (Knowledge-Box, Panic Button, Third Ear, Meditime, Daily Companion, Diary, Encourage, and Self-Discovery). Likewise, the results display that the TidyHome app shows effective usability and user experience. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Player Personality Traits and the Effectiveness of a Persuasive Game for Disease Awareness Among the African Population

Although persuasive gamified systems have been proven to be effective at motivating behaviour change in various domains of life, there are reoccurring research questions around the effectiveness of these systems for players with various user characteristics, cultures, and across various behaviour domains. Our paper explores the effectiveness of various persuasive strategies implemented in a persuasive game for disease awareness and prevention, specifically, persuasive games for creating awareness about COVID-19 among the African audience and the impact of user personality traits on the effectiveness of the strategies. An in-the-wild study among 51 Africans reveals that the 12 persuasive strategies implemented in the game were perceived as highly effective at motivating behaviour change overall. We also uncovered that people high in Agreeableness were motivated by eight of the strategies, while people high in Neuroticism were demotivated by the Self-Monitoring strategy. Agreeableness and Conscientiousness emerged as the personality traits that predicted most of the variability in the effectiveness of the persuasive strategies implemented in the game. Based on the findings and the qualitative comments, we provide design suggestions for implementing various persuasive strategies for different personality traits in the African population. © 2022, Springer Nature Switzerland AG.

Age and the persuasiveness of a game to promote the adoption of COVID-19 precautionary measures

Research has shown that there are differences in how various age groups respond to persuasive attempts. However, there is little knowledge on whether age influences the effectiveness of persuasive games for health, specifically, games for promoting the adoption of COVID-19 precautionary measures. To advance research in this area, we designed COVID Pacman-C-a persuasive game to promote the adoption of COVID-19 precautionary measures employing the competition strategy. This paper presents the design, implementation, and evaluation of COVID Pacman-C to examine its effectiveness with respect to the overall perceived persuasiveness as well as the effect of age on the persuasiveness to establish whether there is a need to tailor the game to various age groups. The results of the study (N=131) followed by a semi-structured interview of 18 participants reveals that the game is perceived as highly persuasive overall with respect to its ability to promote the adoption of the COVID-19 precautionary measures as well as by the different age groups. The findings also revealed that there are significant differences in the persuasiveness for people belonging to different age groups with respect to its ability to motivate them to adopt the COVID-19 precautionary measures. © 2021 IEEE.

Analyzing COVID-19 Tweets using Health Behaviour Theories and Machine Learning

In order to explain people's health habits, Health Behaviour Theories have been used to analyze posts on social media during previous incidents. Regarding the COVID-19 pandemic, social media data can expose public attitudes and experiences, as well as reveal elements that impede or encourage attempts to reduce the spread of the disease. This paper aims to use Health Behaviour Theories (Health Belief Model, Social Norm, and Trust) and Machine Learning to investigate or examine people's behaviours and reactions toward COVID-19. First, we extract COVID-19 comments on Twitter and use candidate keyphrases representing each health behaviour construct to label the comments. Next, we develop three machine learning models/classifiers-Support Vector Machine (SVM), Decision Tree (DT) and Logistic Regression (LR)-to automatically classify comments into appropriate constructs. We train and evaluate the models using 10-fold cross-validation and compare their performance based on precision, recall, and Fl-score metrics. Our results show that DT and SVM perform best with an overall Fl-score of up to 98% for multiclass (single label) classification, while DT outperform other classifiers with an overall Fl-score of up to 100% for multiclass-multilabel classification. Finally, we conduct thematic analysis of the comments in each construct to identify meaningful themes that represent key issues related to the COVID-19 pandemic. Our findings reveal 31 themes across all constructs. © 2021 IEEE.

COVID Dodge: An African-Centric game for promoting COVID-19 Safety Measures

Raising awareness for safety measures against communicable diseases helps reduce the spread among human populations. As the lockdown rules for the COVID-19 pandemic are being relaxed, there is a need for active awareness around the safety measures against the spread of the virus to prevent a second pandemic wave. Therefore, this demonstration paper presents the design and implementation of a mobile persuasive game, titled COVID Dodge, aimed at raising the awareness around social distancing and other precautionary measures against the spread of the COVID-19. This persuasive game employs some strategic features to increase the attention of Africans towards social distancing. © 2021 Owner/Author.

Heuristic Evaluation of an African-centric Mobile Persuasive Game for Promoting Safety Measures against COVID-19

The COVID-19 pandemic affected the whole world, including the African Population. As the lockdown rules against the spread of COVID-19 pandemic are being eased off and Africans have begun going about their normal daily activities, there is a need for interventions and measures to ensure that they continue to observe the safety guidelines to prevent a second wave of the pandemic. While several interventions are emerging, there is a limited number of games or gamified interventions aimed at raising awareness about these safety guidelines with a specific focus on Africans. Games and gamified applications are popular among Africans especially young people due to their entertainment value. Therefore, we present the design, implementation and heuristic evaluation of a mobile persuasive game, titled COVID Dodge, aimed at raising awareness on the importance of social distancing and other precautionary measures against the spread of the COVID-19. This persuasive game strategically employs popular persuasive features and strategies to increase the attention of Africans towards social distancing and other precautionary measures. The results of the heuristic evaluation (Heuristic Evaluation for Playability) revealed that the game possessed a high level of playability which implies that it would be engaging and enjoyed by users. The result of the persuasive strategy evaluation revealed that 13 out of the 15 strategies we implemented were strongly present in the game. Based on the evaluators' comments, we provided some design consideration and insights for developing persuasive games. © 2021 ACM.