Abstract
Online social networks have become a common medium of communications. Studies have shown that it is more likely for a user to share their opinions and ideation. In spite of the fact that this could be beneficial, there are some developing concerns with respect to its negative effect on the users, such as, the spread of self-destructive ideation. According to the World Health Organization (WHO), more than 800,000 people die by suicide each year, a number that translates to one death every 40 seconds. Thus, this study aims to detect suicidal ideation from tweets based from pronouns and absolutist words weights using TF-IDF (Term Frequency – Inverse Document Frequency). Furthermore it will evaluate the performance of two machine classifiers in identifying suicide-related text from Twitter (tweets) using Rapid Miner.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.