Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{152589,
        author = {A. Punitha and U.S. Harshanaa and B. Vanitha and K. Kiruthigaipriya},
        title = {Sentiment Analysis for Depression based on Social Media Stream},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {8},
        number = {3},
        pages = {925-929},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=152589},
        abstract = {This project deals with depression. Around 70% of the people will never consult doctors at an early stage of depression. Instead of it, people commonly start relying on online platform for sharing their depressions, emotions, and daily life activities in it. The existing system using knowledge based recommendation system, the inputs are extracted from online social network then they are filtered by eSM2 sentiment metric to detect depression or stress conditions , ontology collections is used to understand the related information .The filtered sentences are processed using Convolutional Neural Network with bidirectional long short term memory -Recurrent neural network. This system unable to process the unusual symbol, stop words and punctuation and major drawback of this system aid of human is need to extract and feed the inputs to the system. The time consumption of this system is been slow to process huge amount of data to be trained.

In order to overcome this, we propose a real-time chat application, in which people interaction sentiments are stored in chat-server, and also this model includes Support Vector Machine, a machine learning technique is used to handle the mental discomfort of person in a better way. With this technique, analyzing the posts like chats, unusual symbols, stop words, numeric and punctuation on depressive and stressful content and it predict their sentiments like positive, negative and neutral signs. According to the prediction it sends the consolation quote to respective person and intimation of the person discomfort to the organization by using SMTP and MIME protocol. With the help of trained dataset, the time consumption is reduced and gains better accuracy in the prediction.},
        keywords = {Support Vector Machine, sentiment analysis, SMTP.},
        month = {},
        }