An Unsupervised Learning Approach for Automatically to Categorize Potential Suicide Messages in Social Media

Suicide Risk Assessment Using Machine Learning and Social Networks: a Scoping Review

“…From the full-text review, 16 articles were then selected for inclusion [26,[42][43][44][45][46][47][48][49][50][51][52][53][54][55][56]. The flow diagram representing the search process is shown in Fig.…”

“…Parraga-Alava et al 2019 [26] present an approach to categorize potential suicide messages in social media, which is based on unsupervised learning using traditional clustering algorithms. The computational results showed that Hierarchical Clustering Algorithm (HCA) was the best model for binary clustering achieving average rates of 79% and 87% of F1-score for English and Spanish.…”

“…Most of the included studies propose models to classify collected text into suicide-related categories. Text classification is the most common objective in the included studies (12/16, 75%) [26,[42][43][44][45][46][47][48][51][52][53][54]. A score estimation of suicidal probability based on post content was proposed in one of the included studies (1/16, 6,25%) [56].…”

“…Zhang et al [56], recruited potential participants, and then, the selected participants' posts in Weibo have even used. Finally, two studies that used GSNs did not define inclusion/exclusion criteria (2/13, 15.38%) [26,55].…”

“…On the other hand, unsupervised models do not require training. However, these models need datasets for validation [26].…”