Related Experiment Video
Updated: Oct 26, 2025
08:53
Integrating Computerized Linguistic and Social Network Analyses to Capture Addiction Recovery Capital in an Online Community
Published on: May 31, 2019
5.4K
Suicidality Detection on Social Media Using Metadata and Text Feature Extraction and Machine Learning.
Summary
Machine learning models can detect suicidality on Twitter by analyzing post content and metadata. Replies, afternoon posts, and weekend/fall tweets are more likely to be flagged, improving detection accuracy.
Area of Science:
- Computational social science
- Artificial intelligence in mental health
Background:
- Social media platforms like Twitter are increasingly used for communication, making them a potential source for identifying individuals at risk of suicide.
- Previous research has explored text-based features for suicide risk detection, but the role of metadata remains underexplored.
Purpose of the Study:
- To develop and evaluate machine learning models for detecting suicidality in Twitter posts.
- To investigate the significance of metadata features in enhancing the accuracy of suicidality detection models.
Main Methods:
- A dataset of 20,000 randomly selected and annotated Twitter posts was utilized.
- Machine learning models were trained and evaluated using both text and metadata features.
- Metadata features, including posting type and time-related information, were analyzed in detail.
Main Results:
- Posting type (reply vs. original tweet) and time-related features (month, day of the week, AM/PM) were identified as crucial metadata for suicidality detection.
- Suicidality tweets were found to be more probable in replies, during afternoons, on Fridays, weekends, and in the fall season.
- Integrating metadata and text features yielded a high-performing model with an F1 score of 0.846.
Conclusions:
- Metadata features significantly contribute to the accuracy of machine learning models for detecting suicidality on Twitter.
- The developed model demonstrates practical utility in assisting human moderators in identifying at-risk social media content.
- Further research can leverage these findings to build more sophisticated and effective suicide prevention tools for social media platforms.
More Related Videos
Related Concept Videos
01:19MALDI-TOF Mass Spectrometry
5.9K
Mass spectrometry is a powerful characterization technique that can identify and separate a wide variety of compounds ranging from chemical to biological entities, based on their mass-to-charge ratio (m/z). The instruments that allow this detection, known as mass spectrometers, have three components: an ion source, a mass analyzer, and a detector. These spectrometers differ based on the nature of their ion source and analyzers.
Matrix-assisted laser desorption ionization (MALDI) is a commonly...
Matrix-assisted laser desorption ionization (MALDI) is a commonly...
5.9K
01:30Social Foundations of Self IV: Self in Digital Communication
36
Since the early 2000s, computer-mediated communication (CMC) has grown rapidly, playing a crucial role in self-development. A key distinction between CMC and real-life interactions is the lack of a physically present partner. This absence makes non-verbal cues such as facial expressions, body language, and paralinguistic signals unavailable in CMC platforms like email, instant messaging, or social media. The lack of these cues can create ambiguity and complicate how feedback is interpreted.The...
36