Exploring relationships between attitudes toward reducing mental illness stigma and help-seeking on a major Taiwanese online discussion forum: a machine learning approach

Mental health literacy is critical to improving timely access to mental health care, but persistent stigma and negative attitudes toward seeking help remain significant barriers. Social media platforms offer real-time insights into how users express such attitudes and behaviors. This study examined the associations of stigma-reduction attitudes and help-seeking attitudes with subsequently reported help-seeking behaviors. We analyzed 1,506,333 posts from eight mental health–related boards on PTT, a Taiwanese online forum, from January 2018 to January 2024. Bidirectional Encoder Representations from Transformers (BERT) models trained on manually annotated posts scored stigma reduction attitudes, help-seeking attitudes, and help-seeking behaviors (help-seeking behavior detection: F1 = 0.84, accuracy = 0.87; attitude scoring: macro-F1 = 0.67–0.78, accuracy = 0.87–0.93). Logistic regression was used to examine associations between user-level attitude scores derived from posts within a 3-month observation window and subsequent help-seeking behavior. Each one-point increase in stigma reduction attitudes was associated with 1.33-fold higher odds of subsequent help-seeking, whereas continuous help-seeking attitudes were not significant. In dichotomized analyses, stronger stigma reduction and more positive help-seeking attitudes had 1.66- and 1.72-fold higher odds, respectively, although the latter warrants caution. These findings inform culturally sensitive strategies to enhance mental health service utilization.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-21
DOI
https://doi.org/10.1038/s41598-026-82038-z
Primary Topic
Mental Health Treatment and Access
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Exploring relationships between attitudes toward reducing mental illness stigma and help-seeking on a major Taiwanese online discussion forum: a machine learning approach

Hsiao-Ting Huang, Hsin‐Pei Feng, Jia-Ling Koh, Yin‐Ju Lien et al.
Scientific Reports
Mental Health Treatment and Access
article

Exploring relationships between attitudes toward reducing mental illness stigma and help-seeking on a major Taiwanese online discussion forum: a machine learning approach

Hsiao-Ting Huang, Hsin‐Pei Feng, Jia-Ling Koh, Yin‐Ju Lien, Sih-Yu Cian, Chao-Hui Chen
article en

Abstract

Mental health literacy is critical to improving timely access to mental health care, but persistent stigma and negative attitudes toward seeking help remain significant barriers. Social media platforms offer real-time insights into how users express such attitudes and behaviors. This study examined the associations of stigma-reduction attitudes and help-seeking attitudes with subsequently reported help-seeking behaviors. We analyzed 1,506,333 posts from eight mental health–related boards on PTT, a Taiwanese online forum, from January 2018 to January 2024. Bidirectional Encoder Representations from Transformers (BERT) models trained on manually annotated posts scored stigma reduction attitudes, help-seeking attitudes, and help-seeking behaviors (help-seeking behavior detection: F1 = 0.84, accuracy = 0.87; attitude scoring: macro-F1 = 0.67–0.78, accuracy = 0.87–0.93). Logistic regression was used to examine associations between user-level attitude scores derived from posts within a 3-month observation window and subsequent help-seeking behavior. Each one-point increase in stigma reduction attitudes was associated with 1.33-fold higher odds of subsequent help-seeking, whereas continuous help-seeking attitudes were not significant. In dichotomized analyses, stronger stigma reduction and more positive help-seeking attitudes had 1.66- and 1.72-fold higher odds, respectively, although the latter warrants caution. These findings inform culturally sensitive strategies to enhance mental health service utilization.

Scientific Reports
National Taiwan Normal University (TW), National Defense Medical Center (TW)
Mental Health Treatment and Access
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon