# Machine Learning Algorithms for Depression Detection and Their Comparison

**Authors:** Danish Muzafar, Furqan Yaqub Khan, Mubashir Qayoom  
**arXiv:** [2301.03222](https://arxiv.org/abs/2301.03222)  
**Date:** 2023-01-09  
**Summary page:** https://www.summarizepaper.com/en/paper/2301.03222v1/

## Key points

- The article explores the role of textual emotional intelligence in leveraging human emotions on social media platforms.
- Social media platforms have emotional content that can be leveraged for various purposes such as opinion mining, emotion mining, and sentiment analysis.
- Data analysis is used to prevent online bullying, suicide prevention, and depression detection among social media users.
- The authors designed an automatic depression detection system for online social media users by analyzing their social media behavior.
- The designed depression detection classification can effectively mine user's social media interactions to determine whether a social media user is suffering from depression or not.
- The underlying classifier uses state-of-the-art technology in emotional artificial intelligence which includes LSTM (Long Short Term Memory) and other machine learning classifiers.
- The highest accuracy of the classifier is around 70% of LSTM and for SVM the highest accuracy is 81.79%.
- This research highlights the potential of using machine learning algorithms to detect depression among social media users through their online behavior.
- This has important implications for mental health professionals who can use this information to identify individuals who may be at risk and provide appropriate support.

## Summary

The article "Machine Learning Algorithms for Depression Detection and Their Comparison" by Danish Muzafar, Furqan Yaqub Khan, and Mubashir Qayoom explores the role of textual emotional intelligence in leveraging human emotions on social media platforms. Social media platforms are privileged with emotional content that can be leveraged for various purposes such as opinion mining, emotion mining, and sentiment analysis. This data analysis is also used to prevent online bullying, suicide prevention, and depression detection among social media users. The authors designed an automatic depression detection system for online social media users by analyzing their social media behavior. The designed depression detection classification can effectively mine user's social media interactions to determine whether a social media user is suffering from depression or not. The underlying classifier uses state-of-the-art technology in emotional artificial intelligence which includes LSTM (Long Short Term Memory) and other machine learning classifiers. The article presents the results of training the classifier on datasets widely used in literature for emotion mining tasks. The highest accuracy of the classifier is around 70% of LSTM and for SVM the highest accuracy is 81.79%. A confusion matrix of results is also provided. Overall, this research highlights the potential of using machine learning algorithms to detect depression among social media users through their online behavior. This has important implications for mental health professionals who can use this information to identify individuals who may be at risk and provide appropriate support.