Machine Learning Algorithms for Depression Detection and Their Comparison

TL;DR

This paper compares various machine learning algorithms, including LSTM and SVM, for automatic depression detection on social media, achieving up to 81.79% accuracy, to aid mental health monitoring.

Contribution

It introduces a depression detection classifier using advanced emotional AI techniques and compares the performance of different machine learning models on social media data.

Findings

SVM achieved 81.79% accuracy in depression detection.

LSTM achieved up to 70% accuracy.

The classifiers were trained on widely used emotion mining datasets.

Abstract

Textual emotional intelligence is playing a ubiquitously important role in leveraging human emotions on social media platforms. Social media platforms are privileged with emotional content and are leveraged for various purposes like opinion mining, emotion mining, and sentiment analysis. This data analysis is also levered for the prevention of online bullying, suicide prevention, and depression detection among social media users. In this article, we have designed an automatic depression detection of online social media users by analyzing their social media behavior. The designed depression detection classification can be effectively used to mine user's social media interactions and one can determine whether a social media user is suffering from depression or not. The underlying classifier is made using state-of-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%. We trained the classifier on the datasets that are widely used in literature for emotion mining tasks. A confusion matrix of results is also given.