In recent times, there is a huge increase in the usage of social media to share one’s opinion, feelings and even daily activities. By predicting the mood of the users in social media, we can identify the users who discuss or express suicide-related information. Prediction of user’s mood based on the likes, shares and status posted by them on social media is a challenging task as the mood of users change frequently. In this paper, a scheme is proposed to predict the user’s mood based on the likes, shares and status posted in social media and identify the users in the state of depression. This scheme classifies the mood of user as happy, sad, neutral, angry etc. using deep learning. It presents news feeds to keep the depressed user happy and enthusiastic. When the user is in a prolonged state of depression, the alert system alerts the top five users in his/her friend list. This scheme predicts the mood of the users with accuracy around 87%. Further, time critical information is sent to some users who regularly share information such that it reaches all the users within a certain period of time.

Mood Prediction, Social Media, Alert System, Time Critical Information, Depression, News Feed

[1] M. Roshanaei, R. Han, S. Mishra, “Features for mood prediction in social media”, In the proceedings of IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 1580-1581, 2015.
[2] A. Hepburn, “Facebook statistics, stats & facts for 2011”, Digital Buzz, Accessed 31 January 2018.
[3] D. Noyes, “The top 20 valuable Facebook statistics”, Zephoria, Florida, Accessed 10 February 2018.
[4] P. Chiranjeevi, V. Gopalakrishnan, P. Moogi, “Neutral face classification using personalized appearance models for fast and robust emotion detection”, IEEE Transactions on Image Processing ,vol. 24, no. 9, pp.2701-2711, 2015.
[5] G. T. Giancristofaro, A. Panangadan, “Predicting Sentiment towards Transportation in Social Media using Visual and Textual Features”, In the proceedings of the 19th IEEE International Conference on Intelligent Transportation Systems (ITSC), pp. 2113-2118, 2016.
[6] Md. Z. Uddin, W. Khaksar, J. Torresen, “Facial Expression Recognition Using Salient Features and Convolutional Neural Network”, IEEE Access, vol. 5, pp.26146-26161, 2017.
[7] M. Tasviri, S. A. H. Golpayegani, H. Ghavamipoor, “Presenting a Model Based on Social Network Analysis in Order to Offer a Diet to Users Proper to Their Mood”, In the proceedings of the 3th International Conference on Web Research (ICWR), pp. 133-139, 2017.
[8] A. Cernian, A. Olteanu, D. Carstoiu, C. Mares “Mood Detector – On Using Machine Learning to Identify moods and Emotions”, In the proceedings of the 21st International Conference on Control Systems and Computer Science, pp. 213-216, 2017.
[9] Z. Zhu, H. F. Satizabal, U. Blanke, A. Perez-Uribe, G.Troster “Naturalistic Recognition of Activities and Mood Using Wearable Electronics”, IEEE Transactions on Affective Computing, vol. 7, no.3, pp.272-285, 2016.
[10] S.Taylor, E.Nosakhare, A. Sano, R. Picard, “Personalized Multitask Learning for Predicting Tomorrow’s Mood, Stress, and Health”, IEEE Transactions on Affective Computing, vol. 14, no. 8, 2017.
[11] Y. Suhara, Y. Xu, A. Pentland, “Deepmood: Forecasting depressed mood based on self-reported histories via recurrent neural networks”, In the proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, pp. 715–724, 2017.
[12] A. Kaur, R. Malhotra, “Application of random forest in predicting fault-prone classes”, In the procedings of the IEEE International Conference on Advanced Computer Theory and Engineering, pp. 37-43, 2008.
[13] A. Gepp, K. Kumar, S. Bhattacharya, “Business failure prediction using decision trees”, Journal of forecasting, vol. 29, no. 6, pp. 536-555, 2010.
[14] K. Lee, D. Palsetia, R. Narayanan, M.M.A. Patwary, A. Agrawal, A. Choudhary, “Twitter trending topic classification”, In the proceedings of 11th IEEE International Conference on Data Mining Workshops (ICDMW), pp. 251-258, 2011.
[15] L.Breiman, “Bagging predictors”, Machine learning, vol.24, no.2, pp.123-140, 1996.
[16] R. Tarjan, “Depth-first search and linear graph algorithms”, SIAM journal on computing, vol. 1, no. 2, pp.146-160, 1972.