Psychological Stress Detection Using Transformer-Based Models

Stress is a significant mental health problem that results in a lack of concentration. It has been more widely identified through social media since people who are under stress usually post about their physical pain and tiredness. However, stress assessment through social media by professionals can...

Full description

Saved in:
Bibliographic Details
Main Authors: Derwin Suhartono, Irfan Fahmi Saputra, Andhika Rizki Pratama, Gabriel Nathaniel
Format: Article
Language:English
Published: Bina Nusantara University 2024-06-01
Series:ComTech
Subjects:
Online Access:https://journal.binus.ac.id/index.php/comtech/article/view/11105
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849708090740441088
author Derwin Suhartono
Irfan Fahmi Saputra
Andhika Rizki Pratama
Gabriel Nathaniel
author_facet Derwin Suhartono
Irfan Fahmi Saputra
Andhika Rizki Pratama
Gabriel Nathaniel
author_sort Derwin Suhartono
collection DOAJ
description Stress is a significant mental health problem that results in a lack of concentration. It has been more widely identified through social media since people who are under stress usually post about their physical pain and tiredness. However, stress assessment through social media by professionals can be expensive and time-consuming. The research aimed to produce a stress detection system trained using a Twitter dataset to predict stress using the user’s input sentence. The experiments that were done in the research used transformer-based models such as Bidirectional Encoder Representations from Transformers (BERT) and Robustly Optimized BERT (RoBERTa). The research involved data pre-processing, model training, and model evaluation to ensure high-quality train data. Since the data were imbalanced, data trimming was performed in pre-processing to select data randomly until the balance matched. This process ensured the model’s effectiveness in the training and evaluation stages. The features used in these experiments were features from each pre-trained model. In evaluating the model, accuracy, loss, and F1 score were used as metrics. In the result, for BERT, accuracy reaches 0.848 with an F1 score of 0.847. Meanwhile, RoBERTa has an accuracy of 0.837 and 0.834. The results prove that BERT and RoBERTa can be used to classify stress with accuracy and an F1 score above 0.8. The experiment result shows that the BERT deep learning model can detect stress using the Twitter datasets.
format Article
id doaj-art-354883ee8ea24fe6b4b836997b9cf90f
institution DOAJ
issn 2087-1244
2476-907X
language English
publishDate 2024-06-01
publisher Bina Nusantara University
record_format Article
series ComTech
spelling doaj-art-354883ee8ea24fe6b4b836997b9cf90f2025-08-20T03:15:47ZengBina Nusantara UniversityComTech2087-12442476-907X2024-06-01151657110.21512/comtech.v15i1.1110510179Psychological Stress Detection Using Transformer-Based ModelsDerwin Suhartono0Irfan Fahmi Saputra1Andhika Rizki Pratama2Gabriel Nathaniel3Bina Nusantara UniversityBina Nusantara UniversityBina Nusantara UniversityBina Nusantara UniversityStress is a significant mental health problem that results in a lack of concentration. It has been more widely identified through social media since people who are under stress usually post about their physical pain and tiredness. However, stress assessment through social media by professionals can be expensive and time-consuming. The research aimed to produce a stress detection system trained using a Twitter dataset to predict stress using the user’s input sentence. The experiments that were done in the research used transformer-based models such as Bidirectional Encoder Representations from Transformers (BERT) and Robustly Optimized BERT (RoBERTa). The research involved data pre-processing, model training, and model evaluation to ensure high-quality train data. Since the data were imbalanced, data trimming was performed in pre-processing to select data randomly until the balance matched. This process ensured the model’s effectiveness in the training and evaluation stages. The features used in these experiments were features from each pre-trained model. In evaluating the model, accuracy, loss, and F1 score were used as metrics. In the result, for BERT, accuracy reaches 0.848 with an F1 score of 0.847. Meanwhile, RoBERTa has an accuracy of 0.837 and 0.834. The results prove that BERT and RoBERTa can be used to classify stress with accuracy and an F1 score above 0.8. The experiment result shows that the BERT deep learning model can detect stress using the Twitter datasets.https://journal.binus.ac.id/index.php/comtech/article/view/11105stress detectiontransformer-based modelbidirectional encoder representations from transformers (bert)robustly optimized bert (roberta)
spellingShingle Derwin Suhartono
Irfan Fahmi Saputra
Andhika Rizki Pratama
Gabriel Nathaniel
Psychological Stress Detection Using Transformer-Based Models
ComTech
stress detection
transformer-based model
bidirectional encoder representations from transformers (bert)
robustly optimized bert (roberta)
title Psychological Stress Detection Using Transformer-Based Models
title_full Psychological Stress Detection Using Transformer-Based Models
title_fullStr Psychological Stress Detection Using Transformer-Based Models
title_full_unstemmed Psychological Stress Detection Using Transformer-Based Models
title_short Psychological Stress Detection Using Transformer-Based Models
title_sort psychological stress detection using transformer based models
topic stress detection
transformer-based model
bidirectional encoder representations from transformers (bert)
robustly optimized bert (roberta)
url https://journal.binus.ac.id/index.php/comtech/article/view/11105
work_keys_str_mv AT derwinsuhartono psychologicalstressdetectionusingtransformerbasedmodels
AT irfanfahmisaputra psychologicalstressdetectionusingtransformerbasedmodels
AT andhikarizkipratama psychologicalstressdetectionusingtransformerbasedmodels
AT gabrielnathaniel psychologicalstressdetectionusingtransformerbasedmodels