Early Detection of Depression: Social Network Analysis and Random Forest Techniques

Abstract

Background Major depressive disorder (MDD) or depression is among the most prevalent psychiatric disorders, affecting more than 300 million people globally. Early detection is critical for rapid intervention, which can potentially reduce the escalation of the disorder. Objective This study used data from social media networks to explore various methods of early detection of MDDs based on machine learning. We performed a thorough analysis of the dataset to characterize the subjects’ behavior based on different aspects of their writings: textual spreading, time gap, and time span. Methods We proposed 2 different approaches based on machine learning singleton and dual. The former uses 1 random forest (RF) classifier with 2 threshold functions, whereas the latter uses 2 independent RF classifiers, one to detect depressed subjects and another to identify nondepressed individuals. In both cases, features are defined from textual, semantic, and writing similarities. Results The evaluation follows a time-aware approach that rewards early detections and penalizes late detections. The results show how a dual model performs significantly better than the singleton model and is able to improve current state-of-the-art detection models by more than 10%. Conclusions Given the results, we consider that this study can help in the development of new solutions to deal with the early detection of depression on social networks.

Evaluation of Korean-Language COVID-19–Related Medical Information on YouTube: Cross-Sectional Infodemiology Study

“…Demand-based infoveillance studies using internet search queries have primarily focused on predicting infectious disease outbreaks, such as Zika, influenza, dengue, and the measles virus [ 17 - 19 ]. Other studies analyzed user’s behavior on social media and proposed a model that was based on machine learning for the early detection of depression and suicidal risk [ 20 , 21 ].…”

Individuals with depression express more distorted thinking on social media

“…The idea that depression is associated with changes in language is supported by previous research. Specifically, it has been shown that individuals with depression more frequently use a variety of terms that describe negative emotions [19][20][21] , first-person pronouns (FPPs) [21][22][23][24][25] , common symptoms 26 and linguistic inquiry and word count (LIWC) categories deemed to correspond to 'absolutist' language 27 . Machine learning approaches have shown good performance with respect to predicting whether social media users have depression [28][29][30] , identifying the most useful term features to render a prediction.…”

Graph Theory: A Comprehensive Survey about Graph Theory Applications in Computer Science and Social Networks

“…These criteria map and measure the links among things (i.e., people-people, people-item, item-item, and so on). SNA is a process of analyzing the social structures through the joint use of networks and GT [119][120][121]. SNA characterizes networked structures represented as graph, where nodes (individual actors, users, or things within a network) and the edges/links (relationships or interactions) that connect these nodes [122].…”