Social Media and Healthcare Technology

Permanent URI for this collection


Recent Submissions

Now showing 1 - 5 of 8
  • Item
    Social Media as a Tool to Look for People with Dementia Who Become Lost: Factors That Matter
    ( 2018-01-03) Tsoi, Kelvin KF ; Zhang, Lingling ; Chan, Nicholas B ; Chan, Felix CH ; Hirai, Hoyee W ; Meng, Helen ML
    This research explored how social media were used to look for people with dementia who went lost, and investigated what features of social media usage were associated with the outcomes of finding. Tweets that were disseminated to find missing people with dementia were collected and clustered by cases. Ten cases were selected as sample cases and traced for the outcomes of finding. Information of the Twitter users who tweeted and retweeted were retrieved and categorized. Descriptive analysis was applied to examine the lost cases and features of social media usage; T-test and chi-square analysis were conducted between outcomes of the lost incidents and key features of tweets and Twitter users. Results indicated that there was no significant association between the average number of tweets and retweets and the outcomes of finding, but social media users, especially the ones with a larger group of followers (audience), such as the media, should be encouraged to spread such information. However, a code of conduct is needed to ensure social media are not abused.
  • Item
    Physician Ratings Published on Healthcare Organizations’ Websites: Are They Biased?
    ( 2018-01-03) Kordzadeh, Nima
    In today’s age of social media, individuals use physician-rating websites (PRWs) to find information about healthcare providers and make decisions on which providers to choose accordingly. In line with this trend, healthcare organizations such as clinics and hospitals offer their own physician-rating platforms and mechanisms. However, a major concern regarding this form of privately-administered rating mechanism is the potentially high level of bias that may make the ratings published on those websites inaccurate and unreliable. In this study, we examined this form of bias. We used two hospital websites and four independent PRWs including RateMDs, HealthGrades, Vitals, and Google Reviews to collect, compare, and analyze patient satisfaction scores associated with a total of 569 physicians working in two hospitals located in Utah. The results of the analysis of variance (ANOVA), paired t-tests, and box plots demonstrated that, as hypothesized, the ratings published on the hospitals’ websites had significantly higher mean values and narrower distributions than those published on the independent PRWs. Our findings offer important implications for research and practice.
  • Item
    Quality and Customer Satisfaction Health Accessibility Framework using Social Media Platform
    ( 2018-01-03) Albarrak, Abdulaziz ; Li, Yan
    Access to healthcare refers to the ability of individuals to obtain needed healthcare services. It is a complex and multidimensional phenomenon, and can be affected by multiple factors. Among these factors are quality and patient satisfaction. In this study, we propose a framework, namely, Quality and Customer Satisfaction Health Accessibility Framework (QCSHAF), that takes into consideration quality and customer satisfaction in measuring health accessibility. The proposed framework utilizes different social media platforms to derive measures for quality and customer satisfaction of a health facility or physician. The framework is evaluated using a case study in three counties in Southern California. The result from the QCSHAF is compared with the E2SFCA method, a most used method in healthcare accessibility. We discuss the similarity and variation in the accessibility index values between the two methods and highlight the theoretical and practical contributions of the study.
  • Item
    Mobile Health Intervention Development Principles: Lessons from an Adolescent Cyberbullying Intervention
    ( 2018-01-03) Ranney, Megan L. ; Pittman, Sarah K. ; Riese, Alison ; Ybarra, Michele ; Huang, Jeff ; Spirito, Anthony ; Rosen, Rochelle
    Mobile health interventions are becoming increasingly popular, yet challenges in developing effective, user-friendly, evidence-based technology-augmented interventions persist. In this paper, we describe the process of developing an acceptable, evidence-based text messaging program for adolescents experiencing cyberbullying in hopes of addressing some of the challenges encountered by many researchers and developers in this area of intervention development. Participants were 23 adolescents with past-year histories of cyber-victimization and online conflict who enrolled in an hour long qualitative interview. Participants were asked to draw from personal experience to provide feedback on intervention content and design. Results focus on the main principles of intervention development for adolescents involved in cyberbullying: listening for the why in interviews, storyboarding to model abstract concepts, and strategies to develop acceptable theory and tone. Design process and final product design are described. The paper closes with final thoughts on the design process of mobile intervention development.
  • Item
    Tweeting Your Mental Health: an Exploration of Different Classifiers and Features with Emotional Signals in Identifying Mental Health Conditions
    ( 2018-01-03) Chen, Xuetong ; Sykora, Martin ; Jackson, Thomas ; Elayan, Suzanne ; Munir, Fehmidah
    Applying simple natural language processing methods on social media data have shown to be able to reveal insights of specific mental disorders. However, few studies have employed fine-grained sentiment or emotion related analysis approaches in the detection of mental health conditions from social media messages. This work, for the first time, employed fine-grained emotions as features and examined five popular machine learning classifiers in the task of identifying users with self-reported mental health conditions (i.e. Bipolar, Depression, PTSD, and SAD) from the general public. We demonstrated that the support vector machines and the random forests classifiers with emotion-based features and combined features showed promising improvements to the performance on this task.