An Attention-Based CNN-BiLSTM Model for Depression Detection on Social Media Text

Simple item page
aut.relation.articlenumber123834
aut.relation.endpage123834
aut.relation.journalExpert Systems with Applications
aut.relation.startpage123834
aut.relation.volume249
dc.contributor.authorPhilip Thekkekara, Joel
dc.contributor.authorYongchareon, Sira
dc.contributor.authorLiesaputra, Veronica
dc.date.accessioned2024-04-23T03:58:37Z
dc.date.available2024-04-23T03:58:37Z
dc.date.issued2024-03-22
dc.description.abstractDepression has long been described as a common mental health disorder and a disease with a set of diagnostic criteria that influences the affected individuals' feelings and behavior. The prevalence of Internet use has augmented people’s openness to share their experiences and struggles, including mental health disorders on social media thus researchers have tried developing classification models for depression detection using various machine learning and deep learning techniques. In this research, we propose a deep learning architecture with an attention mechanism on CNN-BiLSTM (CBA) and provide a comparative analysis to benchmark well-known deep learning models using the public dataset namely CLEF2017. We found that along with F1 score, precision and recall it is also vital to consider the Area under the curve - Receiver operating characteristic curve (AUC-ROC) and Mathews Correlation Coefficient (MCC) metrics for evaluating depression classification models since the MCC considers all the four values of a confusion matrix. Based on our experiments, the CBA model outperforms the existing state of the art model with an overall accuracy of 96.71% and scores of 0.85 and 0.77 for AUC-ROC and MCC, respectively.
dc.identifier.citationExpert Systems with Applications, ISSN: 0957-4174 (Print), Elsevier BV, 249, 123834-123834. doi: 10.1016/j.eswa.2024.123834
dc.identifier.doi10.1016/j.eswa.2024.123834
dc.identifier.issn0957-4174
dc.identifier.urihttp://hdl.handle.net/10292/17457
dc.languageen
dc.publisherElsevier BV
dc.relation.urihttps://www.sciencedirect.com/science/article/pii/S0957417424007000
dc.rights© 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by/nc/4.0/).
dc.rights.accessrightsOpenAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/
dc.subject46 Information and Computing Sciences
dc.subject4608 Human-Centred Computing
dc.subject4611 Machine Learning
dc.subjectBehavioral and Social Science
dc.subjectMental Health
dc.subjectDepression
dc.subjectMental health
dc.subject3 Good Health and Well Being
dc.subject01 Mathematical Sciences
dc.subject08 Information and Computing Sciences
dc.subject09 Engineering
dc.subjectArtificial Intelligence & Image Processing
dc.titleAn Attention-Based CNN-BiLSTM Model for Depression Detection on Social Media Text
dc.typeJournal Article
pubs.elements-id543525
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
An attention based CNN BiLSTM model.pdf
Size:
907.42 KB
Format:
Adobe Portable Document Format
Description:
Journal article
Download
Collections
School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau