Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models

Princess Chinemerem Iloh; Christian Arthur; Raymond Chiong; The Anh Han; Alessandro Di Stefano

doi:10.1007/978-981-95-4963-4_31

Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models

Princess Chinemerem Iloh
, Christian Arthur
, Raymond Chiong
, The Anh Han
, Alessandro Di Stefano

Applied Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Timely detection of suicidal ideation is vital for suicide prevention, as suicide continues to pose a significant global public health challenge. Social media often reflect early signs of suicidal intent, yet many predictive models lack transparency and interpretability. This study proposes an explainable AI framework combining traditional machine learning algorithms (Logistic Regression, Random Forest, SVM) and transformer-based models (BERT, DistilBERT) to detect suicidal intent in social media posts. SHAP is employed to enhance interpretability and provide insight into model decisions. Logistic Regression achieved 93% accuracy, while BERT attained 90%. The proposed framework offers transparent and actionable insights to support mental health professionals in early intervention efforts.

Original language	English
Title of host publication	18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd –5th December, 2025, Proceedings, Part III
Editors	Thanh Tho Quan, Chattrakul Sombattheera, Hoang-Anh Pham, Ngoc Thinh Tran
Place of Publication	Singapore
Pages	375-386
Volume	3
DOIs	https://doi.org/10.1007/978-981-95-4963-4_31
Publication status	Published - 22 Nov 2025

Publication series

Name	Lecture Notes in Computer Science (LNAI)
Number	16355
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1007/978-981-95-4963-4_31

https://hdl.handle.net/1959.11/71755

Handle.net

Persistent link

Cite this

Chinemerem Iloh, P., Arthur, C., Chiong, R., Han, T. A., & Di Stefano, A. (2025). Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models. In T. T. Quan, C. Sombattheera, H.-A. Pham, & N. T. Tran (Eds.), 18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd –5th December, 2025, Proceedings, Part III (Vol. 3, pp. 375-386). (Lecture Notes in Computer Science (LNAI); No. 16355).. https://doi.org/10.1007/978-981-95-4963-4_31

Chinemerem Iloh, Princess ; Arthur, Christian ; Chiong, Raymond et al. / Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models. 18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd –5th December, 2025, Proceedings, Part III. editor / Thanh Tho Quan ; Chattrakul Sombattheera ; Hoang-Anh Pham ; Ngoc Thinh Tran. Vol. 3 Singapore, 2025. pp. 375-386 (Lecture Notes in Computer Science (LNAI); 16355).

@inproceedings{82d640b64f14436181e4b89e03c86f71,

title = "Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models",

abstract = "Timely detection of suicidal ideation is vital for suicide prevention, as suicide continues to pose a significant global public health challenge. Social media often reflect early signs of suicidal intent, yet many predictive models lack transparency and interpretability. This study proposes an explainable AI framework combining traditional machine learning algorithms (Logistic Regression, Random Forest, SVM) and transformer-based models (BERT, DistilBERT) to detect suicidal intent in social media posts. SHAP is employed to enhance interpretability and provide insight into model decisions. Logistic Regression achieved 93\% accuracy, while BERT attained 90\%. The proposed framework offers transparent and actionable insights to support mental health professionals in early intervention efforts.",

author = "\{Chinemerem Iloh\}, Princess and Christian Arthur and Raymond Chiong and Han, \{The Anh\} and \{Di Stefano\}, Alessandro",

year = "2025",

month = nov,

day = "22",

doi = "10.1007/978-981-95-4963-4\_31",

language = "English",

isbn = "9789819549627",

volume = "3",

series = "Lecture Notes in Computer Science (LNAI)",

number = "16355",

pages = "375--386",

editor = "Quan, \{Thanh Tho\} and Chattrakul Sombattheera and Hoang-Anh Pham and Tran, \{Ngoc Thinh\}",

booktitle = "18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd {\textendash}5th December, 2025, Proceedings, Part III",

}

Chinemerem Iloh, P, Arthur, C, Chiong, R, Han, TA & Di Stefano, A 2025, Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models. in TT Quan, C Sombattheera, H-A Pham & NT Tran (eds), 18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd –5th December, 2025, Proceedings, Part III. vol. 3, Lecture Notes in Computer Science (LNAI), no. 16355, Singapore, pp. 375-386. https://doi.org/10.1007/978-981-95-4963-4_31

Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models. / Chinemerem Iloh, Princess; Arthur, Christian; Chiong, Raymond et al.
18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd –5th December, 2025, Proceedings, Part III. ed. / Thanh Tho Quan; Chattrakul Sombattheera; Hoang-Anh Pham; Ngoc Thinh Tran. Vol. 3 Singapore, 2025. p. 375-386 (Lecture Notes in Computer Science (LNAI); No. 16355).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models

AU - Chinemerem Iloh, Princess

AU - Arthur, Christian

AU - Chiong, Raymond

AU - Han, The Anh

AU - Di Stefano, Alessandro

PY - 2025/11/22

Y1 - 2025/11/22

N2 - Timely detection of suicidal ideation is vital for suicide prevention, as suicide continues to pose a significant global public health challenge. Social media often reflect early signs of suicidal intent, yet many predictive models lack transparency and interpretability. This study proposes an explainable AI framework combining traditional machine learning algorithms (Logistic Regression, Random Forest, SVM) and transformer-based models (BERT, DistilBERT) to detect suicidal intent in social media posts. SHAP is employed to enhance interpretability and provide insight into model decisions. Logistic Regression achieved 93% accuracy, while BERT attained 90%. The proposed framework offers transparent and actionable insights to support mental health professionals in early intervention efforts.

AB - Timely detection of suicidal ideation is vital for suicide prevention, as suicide continues to pose a significant global public health challenge. Social media often reflect early signs of suicidal intent, yet many predictive models lack transparency and interpretability. This study proposes an explainable AI framework combining traditional machine learning algorithms (Logistic Regression, Random Forest, SVM) and transformer-based models (BERT, DistilBERT) to detect suicidal intent in social media posts. SHAP is employed to enhance interpretability and provide insight into model decisions. Logistic Regression achieved 93% accuracy, while BERT attained 90%. The proposed framework offers transparent and actionable insights to support mental health professionals in early intervention efforts.

UR - https://link.springer.com/book/10.1007/978-981-95-4963-4

UR - https://doi.org/10.1007/978-981-95-4963-4

U2 - 10.1007/978-981-95-4963-4_31

DO - 10.1007/978-981-95-4963-4_31

M3 - Conference contribution

SN - 9789819549627

SN - 9789819549634

VL - 3

T3 - Lecture Notes in Computer Science (LNAI)

SP - 375

EP - 386

BT - 18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd –5th December, 2025, Proceedings, Part III

A2 - Quan, Thanh Tho

A2 - Sombattheera, Chattrakul

A2 - Pham, Hoang-Anh

A2 - Tran, Ngoc Thinh

CY - Singapore

ER -

Chinemerem Iloh P, Arthur C, Chiong R, Han TA, Di Stefano A. Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models. In Quan TT, Sombattheera C, Pham HA, Tran NT, editors, 18th International Conference, MIWAI 2025, Ho Chi Minh City, Vietnam, 3rd –5th December, 2025, Proceedings, Part III. Vol. 3. Singapore. 2025. p. 375-386. (Lecture Notes in Computer Science (LNAI); 16355). doi: 10.1007/978-981-95-4963-4_31

Explainable Detection of Suicide Intent in Social Media Using Machine Learning and Transformer Models

Abstract

Publication series

UN SDGs

Access to Document

Handle.net

Fingerprint

Cite this