SSN_MLRG1@LT-EDI-ACL2022: Multi-Class Classification using BERT models for Detecting Depression Signs from Social Media Text
2022-05-01LTEDI (ACL) 2022Unverified0· sign in to hype
Karun Anantharaman, Angel S, Rajalakshmi Sivanaiah, Saritha Madhavan, Sakaya Milton Rajendram
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
DepSign-LT-EDI@ACL-2022 aims to ascer-tain the signs of depression of a person fromtheir messages and posts on social mediawherein people share their feelings and emo-tions. Given social media postings in English,the system should classify the signs of depres-sion into three labels namely “not depressed”,“moderately depressed”, and “severely de-pressed”. To achieve this objective, we haveadopted a fine-tuned BERT model. This solu-tion from team SSN_MLRG1 achieves 58.5%accuracy on the DepSign-LT-EDI@ACL-2022test set.