Topic Modeling and User Network Analysis on Twitter during World Lupus Awareness Day

Social support and audience engagement of lupus-related posts on social networking sites in China

Background

Lupus, known as a chronic multisystem autoimmune disease, has become more common in China currently. Above all, most Chinese Lupus patients haven't ample knowledge and adequate understanding of this complicated chronic disease. In recent years, social networking sites have created an interactive environment in which patients can obtain health information and also can exchange personal experiences with others having similar health concerns.

Objective

The overall aim of this study is to develop a better understanding of the social support requested and received during the routine social media use of lupus activists and their referents. In other words. This paper seeks to explore whether the lupus-related posts disseminated on the Sina microblog platform can serve and satisfy the needs of this group.

Methods

Content analysis and descriptive analysis were conducted to ascertain the core topics of lupus-related posts on the Sina microblog. Chi-square tests were performed to determine the differences in types of social support between provision and request groups, as well as engaged and non-engaged groups. Finally, negative binomial regression was undertaken to investigate which types of social support generated more audience engagement.

Results

By analyzing 9822 lupus-related posts derived from the Sina microblog, disease description was the most prominent theme. Evidence is presented which shows that information support was requested and supplied more frequently than emotional and instrumental support. Specifically, information support was provided more than requested, while the instrumental and emotional support provisions were less numerous than the requests. Analysis revealed that posts containing information support provisions attracted more engagement than those with the other five types of social support.

Conclusions

Social networking sites play a critical role on disseminating lupus-related information and provide an interactive space in which users can freely communicate their health conditions and seek peer support. However, health practitioners not only have to present more communication strategies to provide emotional and instrumental support through social media, but also have to boost audience engagement.

The Marketing and Perceptions of Non-Tobacco Blunt Wraps on Twitter

OBJECTIVE

Non-tobacco blunt wraps (N-TBWs), which entered the marketplace in 2017, are being promoted as an alternative to traditional TBWs (e.g., cigarillos) for blunt smoking. The lack of studies on these novel products warrants an investigation. This study was the first to explore blunt smokers' perceptions about N-TBWs and the extent of product marketing on Twitter.

METHODS

A corpus of tweets from Twitter, posted between January 2017 and November 2021, were identified by a Boolean search string (N = 149,343), where 48,695 tweets were classified as relevant by a machine learning algorithm. These relevant tweets were further screened and labeled as promotional or organic based on product URLs, usernames, keywords, or hashtags. Topic modeling using Dirichlet Allocation was then employed for identifying latent patterns of words among relevant tweets. The Social Networking Potential (SNP) score was employed for identifying influential accounts.

RESULTS

Most relevant tweets (89%) were organic, non-promotional expressions about N-TBWs. Account users who only posted non-promotional tweets had a significantly higher SNP than those who only posted promotional tweets. Yet, neither of the two groups of account users consisted of known celebrities. Topic modeling revealed three broad groups of topics (7 in total) denoting the attributes of hemp N-TBWs, interest in non-hemp N-TBWs, and product marketing.

CONCLUSIONS

The large proportion of organic tweets is indicative of the nascency of N-TBWs, which will need to be marketed more extensively if they are to replace cigar products used by blunt smokers.

Exploring the Factors Associated with Mental Health Attitude in China: A Structural Topic Modeling Approach

Mental health attitude has huge impacts on the improvement of mental health. In response to the ongoing damage the COVID-19 pandemic caused to the mental health of the Chinese people, this study aims to explore the factors associated with mental health attitude in China. To this end, we extract the key topics in mental health-related microblogs on Weibo, the Chinese equivalent of Twitter, using the structural topic modeling (STM) approach. An interaction term of sentiment polarity and time is put into the STM model to track the evolution of public sentiment towards the key topics over time. Through an in-depth analysis of 146,625 Weibo posts, this study captures 12 topics that are, in turn, classified into four factors as stigma (n = 54,559, 37.21%), mental health literacy (n = 32,199, 21.96%), public promotion (n = 30,747, 20.97%), and social support (n = 29,120, 19.86%). The results show that stigma is the primary factor inducing negative mental health attitudes in China as none of the topics related to this factor are considered positive. Mental health literacy, public promotion, and social support are the factors that could enhance positive attitudes towards mental health, since most of the topics related to these factors are identified as positive ones. The provision of tailored strategies for each of these factors could potentially improve the mental health attitudes of the Chinese people.

An Application of Machine Learning Techniques to Analyze Patient Information to Improve Oral Health Outcomes

Objective

Various health-related fields have applied Machine learning (ML) techniques such as text mining, topic modeling (TM), and artificial neural networks (ANN) to automate tasks otherwise completed by humans to enhance patient care. However, research in dentistry on the integration of these techniques into the clinic arena has yet to exist. Thus, the purpose of this study was to: introduce a method of automating the reviewing patient chart information using ML, provide a step-by-step description of how it was conducted, and demonstrate this method's potential to identify predictive relationships between patient chart information and important oral health-related contributors.

Methods

A secondary data analysis was conducted to demonstrate the approach on a set of anonymized patient charts collected from a dental clinic. Two ML applications for patient chart review were demonstrated: (1) text mining and Latent Dirichlet Allocation (LDA) were used to preprocess, model, and cluster data in a narrative format and extract common topics for further analysis, (2) Ordinal logistic regression (OLR) and ANN were used to determine predictive relationships between the extracted patient chart data topics and oral health-related contributors. All analysis was conducted in R and SPSS (IBM, SPSS, statistics 22).

Results

Data from 785 patient charts were analyzed. Preprocessing of raw data (data cleaning and categorizing) identified 66 variables, of which 45 were included for analysis. Using LDA, 10 radiographic findings topics and 8 treatment planning topics were extracted from the data. OLR showed that caries risk, occlusal risk, biomechanical risk, gingival recession, periodontitis, gingivitis, assisted mouth opening, and muscle tenderness were highly predictable using the extracted radiographic and treatment planning topics and chart information. Using the statistically significant predictors obtained from OLR, ANN analysis showed that the model can correctly predict >72% of all variables except for bruxism and tooth crowding (63.1 and 68.9%, respectively).

Conclusion

Our study presents a novel approach to address the need for data-enabled innovations in the field of dentistry and creates new areas of research in dental analytics. Utilizing ML methods and its application in dental practice has the potential to improve clinicians' and patients' understanding of the major factors that contribute to oral health diseases/conditions.

Analysis of the Evolution of User Emotion and Opinion Leaders' Information Dissemination Behavior in the Knowledge Q&A Community during COVID-19

Since its emergence in 2019, COVID-19 has quickly triggered widespread public discussion on social media. From 26 February 2020 to 26 September 2020, this study collected data on COVID-19-related posts in the knowledge Q&A community, identified 220 opinion leaders of this community, and used social network analysis and sentiment analysis to analyze the information exchange behavior and emotional evolution of the opinion leaders during COVID-19. The results show that the COVID-19 topic community could be divided into seven main categories. The information dissemination of opinion leader information dissemination network had low efficiency, multiple paths, and a high degree of control. In addition, the emotional evolution of users showed obvious phased characteristics. User emotion changed from initially strong negative to strong positive over the course of the pandemic and eventually tended to be objective and neutral as time passed and the event stabilized.