Paper Type

ERF

Paper Number

1310

Description

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.

Share

COinS
 
Aug 9th, 12:00 AM

Detecting Emotional Distress from Text

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.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.