Automated Depression Detection from Tweets: A Comparison of NLP Techniques

Basit Öğe Kaydı
dc.contributor.authorBalci, Emirhan
dc.contributor.authorSarac, Esra
dc.date.accessioned2025-01-06T17:29:56Z
dc.date.available2025-01-06T17:29:56Z
dc.date.issued2024
dc.description8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024 -- 21 September 2024 through 22 September 2024 -- Malatya -- 203423
dc.description.abstractThis paper aims to classify suicidal ideation as a symptom of depression from social media posts by applying the state-of-the-art classification model BERT (Bidirectional Encoder Representations from Transformers) and three traditional machine learning algorithms for binary classification. Since depression is one of the most prevalent mental health disorders amongst psychiatric disorders, the authors intended to present an experimental analysis of the machine learning classifier results as a comparison of novel depression detection techniques. We utilized undiagnosed user posts from Twitter as our dataset and tested the fine-tuned BERT model by applying hold-out and 10-fold cross-validation techniques. Since the dataset is highly unbalanced, Support Vector Machine (SVM), Naive Bayes, and Random Forest algorithms were employed on the same dataset with and without the oversampling method SMOTE (Synthetic Minority Oversampling Technique). The results demonstrate that traditional machine learning classifiers cannot infer sentiment from data containing various linguistic cues, such as depression symptoms. On the other hand, the state-of-the-art model BERT achieves 99.29% and 99.56% macro and micro-F-measure values, respectively, surpassing traditional machine learning algorithms in terms of these metrics. As a robust solution to depression detection from textual data, the BERT model is more trustworthy than the traditional machine learning classifiers to detect specific cues related to depression and similar mental disorders. This study contributes to the relevant research areas of natural language processing by indicating the performance difference between the BERT model and several traditional machine learning algorithms as a generalized approach for classification tasks. © 2024 IEEE.
dc.identifier.doi10.1109/IDAP64064.2024.10711029
dc.identifier.isbn979-833153149-2
dc.identifier.scopus2-s2.0-85207968438
dc.identifier.urihttps://doi.org/10.1109/IDAP64064.2024.10711029
dc.identifier.urihttps://hdl.handle.net/20.500.14669/1395
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241211
dc.subjectBERT
dc.subjectSentiment Analysis
dc.subjectTransformer Based Learning
dc.titleAutomated Depression Detection from Tweets: A Comparison of NLP Techniques
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu