Novel depression detection technique using Bert on social media

Abstract

The social media platforms are tremendously used nowadays. A huge amount of realistic data are being created everyday. The data are mainly feelings, emotions, mood of a person. The innovative research from these online users data are to predict levels posts such as negative or positive. The blogging sites like twitter, facebook, instagram have become so popular places to express online users thoughts and feelings. The data can be extensively filtered and used for the purpose of analyzing the depression levels. This can be a great platform for deep learning research. The social media tweets and comments are utilized. The two models simple BI-LSTM along with hybrid model of BERT CNN BI-LSTM is implemented. The hybrid model of BERT CNN BI-LSTM which achieves a higher accuracy than other deep learning models and the BERT Model is efficiently handles the different types of social media users data.