• Ajay Jadhav
• Karthik Morab
• Harshavardhana I
• Niranjana H.B

As society becomes more technically advanced, we are more into the digital world. This has also brought numerous mental health issues for the individuals world-wide. Social networking platforms like Facebook and Twitter allows users to share their opinions and thoughts almost every day. This offer users a level of anonymity and provides users to be more uninhibited in their expressions. The objective of this paper is to propose depression detection and analysis of users based on Twitter data using sentiment analysis. Our study to date shows that such dataset that is readily available was too simplistic and most of the labelled depressive data had a word depression, which proves to be major obstacle to the development of this project, so we also aim to create our own a dataset that is designed precisely for depression identification based on tweets. We have evaluated the efficiency of this model using different approaches and the test accuracy was around 83% with test loss of 0.409 and also show that this proposed technique can significantly improve accuracy and classification error rate.

Depression, Social Network Sites (SNS), Data Analysis, Natural Language Processing (NLP), Neural Network (CNN).

"Social Mental Disorder Detection Using Social Media Mining", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.e697-e702, June-2021, Available :http://www.jetir.org/papers/JETIR2106658.pdf

"Social Mental Disorder Detection Using Social Media Mining", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppe697-e702, June-2021, Available at : http://www.jetir.org/papers/JETIR2106658.pdf