SSN_MLRG1@LT-EDI-ACL2022: Multi-Class Classification using BERT models for Detecting Depression Signs from Social Media Text

Abstract

DepSign-LT-EDI@ACL-2022 aims to ascertain the signs of depression of a person from their messages and posts on social media wherein people share their feelings and emotions. Given social media postings in English, the system should classify the signs of depression into three labels namely “not depressed”, “moderately depressed”, and “severely depressed”. To achieve this objective, we have adopted a fine-tuned BERT model. This solution from team SSN_MLRG1 achieves 58.5% accuracy on the DepSign-LT-EDI@ACL-2022 test set.