Exploring Social Media Posts on Lifestyle Behaviors: Sentiment and Content Analysis
Bibliographic record
Abstract
Background: There has been an increase in the prevalence of noncommunicable diseases in Malaysia. This can be prevented and managed through the adoption of healthy lifestyle behaviors, including not smoking, avoiding alcohol consumption, maintaining a balanced diet, and being physically active. The growing importance of using social media to deliver information on healthy behaviors has led health care professionals (HCPs) to lead these efforts. To ensure effective delivery of information on healthy lifestyle behaviors, HCPs should begin by understanding users' current opinions about these behaviors and whether the users are receptive to recommended health practices. Nevertheless, there has been limited research conducted in Malaysia that aims to identify the sentiments and content of posts, as well as how well users' perceptions align with recommended health practices. Objective: This study aims to examine social media posts related to various lifestyle behaviors, by using a combination of sentiment analysis to analyze users' sentiments and manual content analysis to explore the content of the posts and how well users' perceptions align with recommended health practices. Methods: Using keywords based on lifestyle behaviors, posts originating from X (formerly known as Twitter) and published in Malaysia between November and December 2022 were scraped for sentiment analysis. Posts with positive and negative sentiments were randomly selected for content analysis. A codebook was developed to code the selected posts according to content and alignment of users' perceptions with recommended health practices. Results: A total of 3320 posts were selected for sentiment analysis. Significant associations were observed between sentiment class and lifestyle behaviors (χ26=67.64; P<.001), with positive sentiments higher than negative sentiments for all lifestyle behaviors. Findings from content analysis of 1328 posts revealed that most of the posts were about users' narratives (492/1328), general statements (203/1328), and planned actions toward the conduct of their behavior (196/1328). More than half of tobacco-, diet-, and activity-related posts were aligned with recommended health practices, whereas most of the alcohol-related posts were not aligned with recommended health practices (63/112). Conclusions: As most of the alcohol-related posts did not align with recommended health practices, the findings reflect a need for HCPs to increase their delivery of health information on alcohol consumption. It is also important to ensure the ongoing health promotion of the other 3 lifestyle behaviors on social media, while continuing to monitor the discussions made by social media users.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".