Early Suicide Prevention: Depression Level Prediction Using Machine Learning and Deep Learning Techniques for Bangladeshi Facebook Users

Hossen, Imran; Islam, Tohidul; Rashed, Md. Golam; Das, Dipankar

doi:10.1007/978-981-19-2445-3_52

Cited by 4 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the questionnaire datasets, some researchers detected the intensity of depression from text data from various online blogging sites and social networking platforms. Hossen et al [15] worked on binary and two multi-class classification (four classes and six classes) issues for the Facebook posts. The authors proposed LR with the TF-IDF technique for the multi-classification problems, while in binary classification, they suggested LSTM with a wordembedding approach.…”

Section: Depression Detection From the Bengali Contentmentioning

confidence: 99%

“…Compare with related works: The proposed method, MaxOfAvgProb, identifies the severity level of depression from the Bengali text data. To the best of our knowledge, we detected three research works [15]- [17] that dealt with recognizing the level of depression in text for the low-resource Bengali language. Table 7 articulates the comparative overview between the proposed method and the recent related works.…”

Section: Analysis Of Training-validation Accuracy Curvementioning

confidence: 99%

“…Table 7 articulates the comparative overview between the proposed method and the recent related works. Hossen et al [15] achieved better outputs (F1-score is 46.64% and accuracy is 48.00%) using the LR with TF-IDF technique, while Hoque and Salma [17] obtained maximum result with F1-score at 61.11% and accuracy at 60.89% by applying XLM-R-base transformer model for the DSD-1 corpus. However, our proposed approach achieves better results than [17] for the same dataset with 63.47% F1-score and 62.90% accuracy.…”

Section: Analysis Of Training-validation Accuracy Curvementioning

confidence: 99%

“…However, the majority of these studies used traditional ML and DL classifiers to study binary classification problems (depression or not) [9]- [13]. A few investigations dealt with multi-class classification problems from emotional perspectives, such as anger, fear, disgust, sadness, joy, surprise, and others [14], [15]. Moreover, a few scholars developed depression severity detection systems [15]- [17].…”

Section: Introductionmentioning

confidence: 99%

“…A few investigations dealt with multi-class classification problems from emotional perspectives, such as anger, fear, disgust, sadness, joy, surprise, and others [14], [15]. Moreover, a few scholars developed depression severity detection systems [15]- [17]. Consequently, this research employs five transformer models, including multilingual Bidirectional Encoder Representations from Transformers (mBERT), DistilmBERT, XLM-RoBERTa (XLM-R), Bangla-BERT-Base, and BanglaBERT, and designs an effective depression intensity recognition system using a transformer ensemble method, MaxOfAvgProb, from the Bengali text data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Untitled

2024

J. Eng. Adv.

View full text Add to dashboard Cite

Depression is an ordinary mental health-related disorder that hampers people's daily activities, and sometimes, it destroys an individual's life. It is one of the major social issues at present. Since depressed people use various social networking sites for sharing their thoughts and feelings, many scholars have tried to identify depression texts in highly resourced languages like English; however, only a small quantity of papers are detected in the resource-constrained Bengali language. This paper focuses on developing a depression intensity detection system from Bengali text data. In this regard, this study experiments on a 2,596 sample-sized dataset with four levels of depression by utilizing five state-of-the-art transformer models, including multilingual Bidirectional Encoder Representations from Transformers, DistilmBERT, XLM-RoBERTa, Bangla-BERT-Base, and BanglaBERT, and suggests a new ensemble method called MaxOfAvgProb. This method goes beyond the performance of the previous work on the same dataset, scoring 63.47% F1-score and 62.90% accuracy. To increase the reliability of the proposed method, we utilize this approach on another available dataset with 4,897 entries. In this case, our recommended method also surpasses the performance of the existing work on the same dataset, with accuracy at 86.45% and F1-score at 86.35%. Identifying the intensity of depression, depressed people may get proper counseling or treatment from their respected guardians or psychologists according to the victims' level of depression.

show abstract

Section: Depression Detection From the Bengali Contentmentioning

confidence: 99%

Section: Analysis Of Training-validation Accuracy Curvementioning

confidence: 99%

Section: Analysis Of Training-validation Accuracy Curvementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Untitled

2024

J. Eng. Adv.

View full text Add to dashboard Cite

show abstract

BanglaSAPM: A Deep Learning Model for Suicidal Attempt Prediction Using Social Media Content in Bangla

Islam

Forhad

Murad

2022

2022 25th International Conference on Computer and Information Technology (ICCIT)

View full text Add to dashboard Cite

Detecting Level of Depression from Social Media Posts for the Low-resource Bengali Language

Hoque

Salma

2023

J. Eng. Adv.

View full text Add to dashboard Cite

Depression is a mental illness that suffers people in their thoughts and daily activities. In extreme cases, sometimes it leads to self-destruction or commit to suicide. Besides an individual, depression harms the victim's family, society, and working environment. Therefore, before physiological treatment, it is essential to identify depressed people first. As various social media platforms like Facebook overwhelm our everyday life, depressed people share their personal feelings and opinions through these platforms by sending posts or comments. We have detected many research work that experiment on those text messages in English and other highly-resourced languages. Limited works we have identified in low-resource languages like Bengali. In addition, most of these works deal with a binary classification problem. We classify the Bengali depression text into four classes: non-depressive, mild, moderate, and severe in this investigation. At first, we developed a depression dataset of 2,598 entries. Then, we apply pre-processing tasks, feature selection techniques, and three types of machine learning (ML) models: classical ML, deep-learning (DL), and transformer-based pre-trained models. The XLM-RoBERTa-based pre-trained model outperforms with 61.11% F1-score and 60.89% accuracy the existing works for the four levels of the depression-class classification problem. Our proposed machine learning-based automatic detection system can recognize the various stages of depression, from low to high. It may assist the psychologist or others in providing level-wise counseling to depressed people to return to their ordinary life.

show abstract

Early Suicide Prevention: Depression Level Prediction Using Machine Learning and Deep Learning Techniques for Bangladeshi Facebook Users

Cited by 4 publications

References 15 publications

Untitled

Untitled

BanglaSAPM: A Deep Learning Model for Suicidal Attempt Prediction Using Social Media Content in Bangla

Detecting Level of Depression from Social Media Posts for the Low-resource Bengali Language

Contact Info

Product

Resources

About