Open Access Open Access  Restricted Access Subscription Access

Despondency Location Utilizing AI

Mahesh K M, Vimal V K

Abstract


The issue of depression in our society is becoming increasingly significant as more and more people are affected by it. It's a debilitating disorder that can ‘affect people of all ages, and while some may recognize that they have it, others may be unaware. Individuals have started using social media as a platform to record their emotional states, and studies have been carried out utilizing machine learning algorithms to identify depression by analyzing social media posts. By analyzing data available on social media (Twitter), it is possible to determine whether a person is experiencing depression or not. Machine learning algorithms are used to classify the data and identify depressive and non-depressive posts. This proposed system uses Twitter data and various algorithms, such as XGBoost, SVM, Logistic Regression, and Random Forest Classifier, to detect depression. The results were compared based on the highest accuracy level, and it was found that the XGBoost algorithm had the highest accuracy level. A User Interface is introduced for real time classification.


Full Text:

PDF

References


M. Reddy, “Depression: the disorder and the burden,” Indian journal of psychological medicine, vol. 32, no. 1, p. 1, 2010.

M. M. Aldarwish and H. F. Ahmad, “Predicting depression levels using social media posts,” in 2017 IEEE 13th international Symposium on Autonomous decentralized system (ISADS). IEEE, 2017, pp. 277–280.(svm)

“Depression and suicide: Overview, etiology of depression and suicidality, epidemiology of depression and suicide,” Feb 2019. [Online]. Available: https://emedicine.medscape.com/article/805459-overview

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg et al., “Scikit-learn: Machine learning in python,” Journal of machine learning research, vol. 12, no. Oct, pp. 2825–2830, 2011

Park, H. (2013). An introduction to logistic regression: From basic concepts to interpretation with particular attention to nursing domain. Journal of Korean Academy of Nursing, 43(2), 154–164.

Kanakaraj, Monisha, and Ram Mohana Reddy Guddeti. "Performance analysis of Ensemble methods on Twitter sentiment analysis using NLP techniques." Proceedings of the 2015 IEEE 9th international conference on semantic computing (IEEE ICSC 2015). IEEE, 2015.

J. Pennington, R. Socher, C. D. Manning, Glove: Global vectors for word representation, in: Empirical Methods in Natural Language Processing, 2014, pp. 1532—-1543

A gentle introduction to xgboost for applied machine learning,” Sep 2016. [Online]. Available: https://machinelearningmastery.com/ gentle-introduction-xgboost-applied-machine-learning/

Debasish Bhattacharjee Victor; Jamil Kawsher; Md Shad Labib; Subhenur Latif; (2020). Machine Learning Techniques for Depression Analysis on Social Media- Case Study on Bengali Community . 2020. Machine Learning Techniques for Depression Analysis on Social Media- Case Study on Bengali Community | IEEE Conference Publication | IEEE Xplore(random forest)

Python-Creates UIs for prototyping Machine Learning model with Gradio. Python - Create UIs for prototyping Machine Learning model with Gradio - GeeksforGeeks


Refbacks

  • There are currently no refbacks.