Suicidal Posts Detection System Incorporating Psychological Risk Factors

Chih-Ning Chen, Chieh-Jou Lin, Kunhua Lee, Yu Ping Ma, Kuo-Liang Ou, Daw-Wei Wang
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:1214-1229, 2025.

Abstract

Our study aims to utilize psychological risk factors to detect posts on social media that contain high-risk suicidal content in Mandarin. We propose a two-stage model structure: the first stage labels each sentence in an post according to risk factors, while the second stage uses these labels as features to predict the crisis level of the post. Our models were trained using a dataset developed from social media posts on a popular Mandarin-speaking platform, labeled by psychological professionals. Our approach achieved an accuracy and F1-score of 0.96 in classifying posts with high crisis levels. Furthermore, we developed a frontend webpage system to apply our model, designed for use by psychological professionals as an aid. This system not only helps psychological professionals detect and address high-risk posts but also offers them the opportunity for psychological analysis based on risk factors. By integrating expertise from psychology with advanced NLP and deep learning techniques, our system bridges the gap between technical models and psychological insights.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-chen25d, title = {Suicidal Posts Detection System Incorporating Psychological Risk Factors}, author = {Chen, Chih-Ning and Lin, Chieh-Jou and Lee, Kunhua and Ma, Yu Ping and Ou, Kuo-Liang and Wang, Daw-Wei}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {1214--1229}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/chen25d/chen25d.pdf}, url = {https://proceedings.mlr.press/v304/chen25d.html}, abstract = {Our study aims to utilize psychological risk factors to detect posts on social media that contain high-risk suicidal content in Mandarin. We propose a two-stage model structure: the first stage labels each sentence in an post according to risk factors, while the second stage uses these labels as features to predict the crisis level of the post. Our models were trained using a dataset developed from social media posts on a popular Mandarin-speaking platform, labeled by psychological professionals. Our approach achieved an accuracy and F1-score of 0.96 in classifying posts with high crisis levels. Furthermore, we developed a frontend webpage system to apply our model, designed for use by psychological professionals as an aid. This system not only helps psychological professionals detect and address high-risk posts but also offers them the opportunity for psychological analysis based on risk factors. By integrating expertise from psychology with advanced NLP and deep learning techniques, our system bridges the gap between technical models and psychological insights.} }
Endnote
%0 Conference Paper %T Suicidal Posts Detection System Incorporating Psychological Risk Factors %A Chih-Ning Chen %A Chieh-Jou Lin %A Kunhua Lee %A Yu Ping Ma %A Kuo-Liang Ou %A Daw-Wei Wang %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-chen25d %I PMLR %P 1214--1229 %U https://proceedings.mlr.press/v304/chen25d.html %V 304 %X Our study aims to utilize psychological risk factors to detect posts on social media that contain high-risk suicidal content in Mandarin. We propose a two-stage model structure: the first stage labels each sentence in an post according to risk factors, while the second stage uses these labels as features to predict the crisis level of the post. Our models were trained using a dataset developed from social media posts on a popular Mandarin-speaking platform, labeled by psychological professionals. Our approach achieved an accuracy and F1-score of 0.96 in classifying posts with high crisis levels. Furthermore, we developed a frontend webpage system to apply our model, designed for use by psychological professionals as an aid. This system not only helps psychological professionals detect and address high-risk posts but also offers them the opportunity for psychological analysis based on risk factors. By integrating expertise from psychology with advanced NLP and deep learning techniques, our system bridges the gap between technical models and psychological insights.
APA
Chen, C., Lin, C., Lee, K., Ma, Y.P., Ou, K. & Wang, D.. (2025). Suicidal Posts Detection System Incorporating Psychological Risk Factors. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:1214-1229 Available from https://proceedings.mlr.press/v304/chen25d.html.

Related Material