User Centric Social Opinion and Clinical Behavioural Model for Depression Detection

Ayodeji Olusegun Ibitoye,Dauda Odunayo Olanloye,Ehisuoria Akioyamen,Rantiola Fidelix Famutimi

doi:10.11648/j.ijiis.20211004.15

Ayodeji Olusegun Ibitoye, Dauda Odunayo Olanloye + Show 2 more

Open Access

https://doi.org/10.11648/j.ijiis.20211004.15

Copy DOI

Abstract

In more recent time, depression as a lingering mental illness as continued to affect the way people act, and behave consciously or otherwise. Though it remained an undiagnosed disease globally without prejudice to age, gender, color or race; a lot of people never know implicitly or explicitly when they are depressed until it begins to affect their health conditions. While depression can be deciphered through text analysis in opinion mining, oftentimes, changes in human body also provides a convincing status of a depressed individual. No doubt, each data source can independently predict human depression status; however, the exclusive mutual relationship between both data sources has not been studied for depression detection. Therefore, in identifying meaningful correlations between clinical and behavioural data, this research detected depression by analyzing and matching mined patterns in users’ behavioural opinion through tweets with trackable changes in clinical body vitals using wearable device for effective therapy in depressed patient management. Thus, by using a 5-fold cross validation on the clustered data, Random Forest ensemble model was used to build the Social-Health Depression Detection Model (SH2DM) after data preprocessing and optimal feature extraction. The dual data sourced user-centric model produced a better predictive result in accuracy, precision and recall values when compared and evaluated with single data depression detection instances of clinical and behavioural records.

Highlights

In the race for sustainable and better life, everyone has the tendency to feel sometimes down or low, the cognitive functions of the human brain begin to depreciate if the emotional down times of an individual over a longer period remains steady
Due to denial or lack of routine diagnoses among others, in today’s world, depression is being considered as one of the most common mental illness [6], which has been predicted to be the top contributor to Global Burden of Disease (GBD) by 2030 [7]
[22] proposed a depression detection model based on 10 features and 3 classifiers to verify the model on Twitter data while a lexicon of terms was built [23] to identify depression or its symptoms from online opinion mining

Summary

Introduction

In the race for sustainable and better life, everyone has the tendency to feel sometimes down or low, the cognitive functions of the human brain begin to depreciate if the emotional down times of an individual over a longer period remains steady. It is a serious medical condition that can get worse if not properly identified It oftentimes observed in human expression and health condition. In more recent times, monitoring and analyzing depression using a Ayodeji Olusegun Ibitoye et al.: User Centric Social Opinion and Clinical Behavioural Model for Depression Detection wearable sensor with machine learning has continued to provide meaningful insight into getting accurate results on depression implementation [4]. By using Random Forest ensemble model, this research employed learning, monitoring and matching patient’s body vitals with expressed opinion in depression detection for operative therapy. Users public expressions are captured, and they do not need to take body vital readings manually By this provision, a dual depression detection data centered model is implemented using IF-Association rules for better clustering of contributing depression vitals for a more actionable outcome.

Sample Related Works on Depression Detection

Social-Health Depression Detection Predictive Model

Experiments and Evaluations

Findings

Conclusion