Social Media and Healthcare Technology
Permanent URI for this collection
1 - 5 of 5
ItemAn Exploratory Study of Social Media Analysis for Rare Diseases Using Machine Learning Algorithms: A Case Study of Trigeminal Neuralgia( 2020-01-07)Rare diseases, affecting approximately 30 million Americans, are often poorly understood by clinicians due to lack of familiarity with the disease and proper research. Patients with rare diseases are often unfavorably treated, especially those with extremely painful chronic orofacial rare disorders. In the absence of structured knowledge, such patients often choose social media to seek help from peers within patient-oriented social media communities thereby generating tremendous amounts of unstructured data daily. We investigate whether we can organize this unstructured data using machine learning to help members of rare communities find relevant information more efficiently in real-time. We chose Trigeminal Neuralgia (TN), an extremely painful rare disorder, as our case study and collected 20,000 social media TN posts. We categorized TN posts into Twitter (very short), and Facebook (short, medium, long) datasets based on message length and performed three clustering experiments. Results revealed GSDMM outperformed both K-means and Spherical K-means in clustering Facebook especially for short messages in terms of speed. For long messages, MDS reduction outperformed the PCA when both were used with K-means and Spherical K-means. Our study demonstrated the need for further topic modeling to utilize among high level clusters based on semantic analysis of posts within each cluster.
ItemSocial Media Use and Prevention of HIV and Other Sexually Transmitted Infections among At-Risk College Students in the United States( 2020-01-07)The purpose of this study was to evaluate college students' self-perceptions of HIV/STI risk, potential barriers to HIV/STI testing, use of social media, and technology-based HIV/STI health interventions. Surveys were administered to 97 US college students. Participants were categorized into three groups based on sexual behaviors: (1) men who have sex with men (MSM), (2) men who have sex with women (MSW), and (3) women who have sex with men (WSM). MSM (n=24) were significantly more likely MSW/WSM (n=72) to report being tested in the past year for HIV (p<.01) and other STIs (p<.01). Only 35% reported HIV testing and 24% reported STI testing in the past year. MSM were more likely than MSW to report having met a sexual partner through social media (p<.01), while no WSM reported doing so. The average number of partners met online in the past year was 7.8 (range=1-20). Those who had met a partner online were more willing to receive e-mail or text message HIV/STI testing reminders (p<.05).
ItemInsights into Adolescent Online Conflict through Qualitative Analysis of Online Messages( 2020-01-07)Given adolescents’ widespread use of online messaging and social media, as well as the prevalence of cyberbullying, analyzing adolescents’ online message-based communication topics and patterns is relevant to public health. To better describe conflict in adolescent online communication, this paper analyzes patterns of conflict in a dataset of adolescent online messages. We describe a qualitative methodology for analyzing these complex data, to expand understanding of adolescents’ online conversations, and to identify how best to categorize conflict within online media datasets. In this study, 14,239 messages from 20 adolescents in the Northeast United States (of which 1,911 were coded) were analyzed using thematic analysis. Several distinct kinds of conflict and responses were identified. Conflict was either direct or indirect, serious or non-serious; it most often was indirect and serious, referenced either insults or romantic contacts, and was frequently related to in-person fights. Coding relied on understanding both textual contexts and referents.
ItemTopical Mining of Malaria Using Social Media. A Text Mining Approach( 2020-01-07)Malaria is a life-threatening parasitic disease, common in subtropical and tropical climates caused by mosquitoes. Each year, several hundred thousand of people die from malaria infections. However, with the rapid growth, popularity and global reach of social media usage, a myriad of opportunities arises for extracting opinions and discourses on various topics and issues. This research examines the public discourse, trends and emergent themes surrounding malaria discussion. We query Twitter corpus leveraging text mining algorithms to extract and analyze topical themes. Further, to investigate these dynamics, we use Crimson social media analytics software to analyze topical emergent themes and monitor malaria trends. The findings reveal the discovery of pertinent topics and themes regarding malaria discourses. The implications include shedding insights to public health officials on sentiments and opinions shaping public discourse on malaria epidemic. The multi-dimensional analysis of data provides directions for future research and informs public policy decisions.