Detecting emotional distress from text

Michael Chau, Melody M. Chao, Wu Liu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Emotional distress, such as depression, has become a significant problem in modern societies. Previous research has proposed machine learning models to automatically detect emotional distress from online social media texts. However, these approaches have not effectively incorporated domain knowledge into state-of-the-art architectures and have not been tested on writing in a more private context. This paper discusses our proposed plan to address these two research gaps. First, we will design and evaluate a deep learning model that incorporates domain knowledge to detect emotional distress from texts. Second, we will collect texts from both social media platforms and private diary writing to study the differences in the classification performance of the proposed model on these texts.

Original languageEnglish
Title of host publication27th Annual Americas Conference on Information Systems, AMCIS 2021
PublisherAssociation for Information Systems
ISBN (Electronic)9781733632584
Publication statusPublished - Aug 2021
Event27th Annual Americas Conference on Information Systems, AMCIS 2021 - Virtual, Online
Duration: 9 Aug 202113 Aug 2021

Publication series

Name27th Annual Americas Conference on Information Systems, AMCIS 2021

Conference

Conference27th Annual Americas Conference on Information Systems, AMCIS 2021
CityVirtual, Online
Period9/08/2113/08/21

Keywords

  • Deep learning
  • Emotional distress
  • Machine learning
  • Natural language processing

ASJC Scopus subject areas

  • Information Systems

Cite this