Abstract
Changes in human lifestyle have led to an increase in the number of people suffering from depression over the past century. Although in recent years, rates of diagnosing mental illness have improved, many cases remain undetected. Automated detection methods can help identify depressed or individuals at risk. An understanding of depression detection requires effective feature representation and analysis of language use. In this article, text classifiers are trained for depression detection. The key objective is to improve depression detection performance by examining and comparing two sets of methods: hybrid and ensemble. The results show that ensemble models outperform the hybrid model classification results. The strength and effectiveness of the combined features demonstrate that better performance can be achieved by multiple feature combinations and proper feature selection.
Highlights
D RASTIC changes in the human lifestyle in modern society have led to an increase in the number of people suffering from depression
As methods, such as recurrent neural networks (RNNs), long short-term memory (LSTM), and attention-based models, have transformed speech and natural language processing (NLP), this study draws from these models to analyze and classify texts by detecting the fragments containing sentiments
The data points after Principal component analysis (PCA) make up one cluster, suggesting that they correlated with each other [Fig. 4(a) and (b)] as the separation of data points is not very rigid, and this suggests that data points are not very different from each other
Summary
D RASTIC changes in the human lifestyle in modern society have led to an increase in the number of people suffering from depression. Communication entails a broader range of contributors, including understanding the world, social norms, and cultural awareness To address these challenges, recently, research in depression detection has taken top-down approaches to learn by applying symbolic AI methods such as logical reasoning. The hybrid combination of subsymbolic approaches with symbolic methods has been shown to induce more meaningful patterns in natural language texts [13]. In principle, this is an experimental study to show how the hybrid methods (symbolic and subsymbolic) and ensemble methods can improve performance for depression detection. This is an experimental study to show how the hybrid methods (symbolic and subsymbolic) and ensemble methods can improve performance for depression detection For this purpose, eight folds of experiments on each of three separate datasets are conducted. A comparison between these models, concluding remarks, limitations, and further research directions is discussed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
