Making a Case for Social Media Corpus for Detecting Depression

Abstract

The social media platform provides an opportunity to gain valuable insights into user behaviour. Users mimic their internal feelings and emotions in a disinhibited fashion using natural language. Techniques in Natural Language Processing have helped researchers decipher standard documents and cull together inferences from massive amount of data. A representative corpus is a prerequisite for NLP and one of the challenges we face today is the non-standard and noisy language that exists on the internet. Our work focuses on building a corpus from social media that is focused on detecting mental illness. We use depression as a case study and demonstrate the effectiveness of using such a corpus for helping practitioners detect such cases. Our results show a high correlation between our Social Media Corpus and the standard corpus for depression.