Theory-Driven Automated Content Analysis of Suicidal Tweets : Using Typicality-Based Classification for LDA Dataset

TL;DR

This paper introduces a novel automated framework combining supervised and unsupervised methods to classify suicidal tweets based on the Theory of Planned Behavior, revealing insights into the information environment surrounding suicide on Twitter.

Contribution

It presents a new methodology integrating LDA, nearest neighbor, and typicality assessment for classifying tweets according to TPB variables, advancing content analysis techniques.

Findings

Tweets often contain information influencing perceived behavior control of suicide.

Suicide-promoting content is more common than deterrent information.

The framework effectively identifies traits of the Twitter information environment.

Abstract

This study provides a methodological framework for the computer to classify tweets according to variables of the Theory of Planned Behavior. We present a sequential process of automated text analysis which combined supervised approach and unsupervised approach in order to make the computer to detect one of TPB variables in each tweet. We conducted Latent Dirichlet Allocation (LDA), Nearest Neighbor, and then assessed "typicality" of newly labeled tweets in order to predict classification boundary. Furthermore, this study reports findings from a content analysis of suicide-related tweets which identify traits of information environment in Twitter. Consistent with extant literature about suicide coverage, the findings demonstrate that tweets often contain information which prompt perceived behavior control of committing suicide, while rarely provided deterring information on suicide. We conclude by highlighting implications for methodological advances and empirical theory studies.