Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning

Ramit Sawhney, Prachi Manchanda, Puneet Mathur, Rajiv Shah, Raj Singh


Abstract
The increasing suicide rates amongst youth and its high correlation with suicidal ideation expression on social media warrants a deeper investigation into models for the detection of suicidal intent in text such as tweets to enable prevention. However, the complexity of the natural language constructs makes this task very challenging. Deep Learning architectures such as LSTMs, CNNs, and RNNs show promise in sentence level classification problems. This work investigates the ability of deep learning architectures to build an accurate and robust model for suicidal ideation detection and compares their performance with standard baselines in text classification problems. The experimental results reveal the merit in C-LSTM based models as compared to other deep learning and machine learning based classification models for suicidal ideation detection.
Anthology ID:
W18-6223
Volume:
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Alexandra Balahur, Saif M. Mohammad, Veronique Hoste, Roman Klinger
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
167–175
Language:
URL:
https://aclanthology.org/W18-6223
DOI:
10.18653/v1/W18-6223
Bibkey:
Cite (ACL):
Ramit Sawhney, Prachi Manchanda, Puneet Mathur, Rajiv Shah, and Raj Singh. 2018. Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 167–175, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Exploring and Learning Suicidal Ideation Connotations on Social Media with Deep Learning (Sawhney et al., WASSA 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6223.pdf