Suicide related text classification with prism algorithm

Fatima  Chiroma; Han Liu; Mihaela Cocea

doi:10.1109/ICMLC.2018.8527032

Suicide related text classification with prism algorithm

Fatima Chiroma
, Han Liu
, Mihaela Cocea

Cardiff University

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

154 Downloads (Pure)

Abstract

Raw but valuable user data is continuously being generated on social media platforms. This data is, however, more valuable when they are mined using different approaches such as machine learning techniques. Additionally, this user-generated data can be used to potentially save lives especially of vulnerable social media users, as several studies carried out have shown the correlation between social media and suicide. In this study, we aim at contributing to the research relating to suicide communication on social media. We measured the performance of five machine learning algorithms: Prism, Decision Tree, Naive Bayes, Random Forest and Support Vector Machine, in classifying suicide-related text from Twitter. The results of the study showed that the Prism algorithm has outperformed the other machine learning algorithms with an F-measure of 0.84 for the target classes (Suicide and Flippant). This result, to the best of our knowledge, is the highest performance that has been achieved in classifying social media suicide-related text.

Original language	English
Title of host publication	Proceedings of the 2018 International Conference on Machine Learning and Cybernetics (ICMLC)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	575-580
Number of pages	6
Volume	2
ISBN (Electronic)	978-1-5386-5214-5
ISBN (Print)	978-1-5386-5215-2
DOIs	https://doi.org/10.1109/ICMLC.2018.8527032
Publication status	Published - 12 Nov 2018
Event	2018 International Conference on Machine Learning and Cybernetics - http://www.icmlc.com/icmlc/welcome.html, Chengdu, China Duration: 15 Jul 2018 → 18 Jul 2018

Publication series

Name	International Conference on Machine Learning and Cybernetics (ICMLC)
Publisher	IEEE
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	2018 International Conference on Machine Learning and Cybernetics
Abbreviated title	ICMLC 2018
Country/Territory	China
City	Chengdu
Period	15/07/18 → 18/07/18

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Text classification
Machine Learning
Prism
Social media
Suicide

Access to Document

10.1109/ICMLC.2018.8527032

ICMLC22018
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 179 KB

Cite this

Chiroma, F., Liu, H., & Cocea, M. (2018). Suicide related text classification with prism algorithm. In Proceedings of the 2018 International Conference on Machine Learning and Cybernetics (ICMLC) (Vol. 2, pp. 575-580). (International Conference on Machine Learning and Cybernetics (ICMLC)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLC.2018.8527032

@inproceedings{6ebc29c5a4f54c81b0b4e8823703ecbd,

title = "Suicide related text classification with prism algorithm",

abstract = "Raw but valuable user data is continuously being generated on social media platforms. This data is, however, more valuable when they are mined using different approaches such as machine learning techniques. Additionally, this user-generated data can be used to potentially save lives especially of vulnerable social media users, as several studies carried out have shown the correlation between social media and suicide. In this study, we aim at contributing to the research relating to suicide communication on social media. We measured the performance of five machine learning algorithms: Prism, Decision Tree, Naive Bayes, Random Forest and Support Vector Machine, in classifying suicide-related text from Twitter. The results of the study showed that the Prism algorithm has outperformed the other machine learning algorithms with an F-measure of 0.84 for the target classes (Suicide and Flippant). This result, to the best of our knowledge, is the highest performance that has been achieved in classifying social media suicide-related text.",

keywords = "Text classification, Machine Learning, Prism, Social media, Suicide",

author = "Fatima Chiroma and Han Liu and Mihaela Cocea",

year = "2018",

month = nov,

day = "12",

doi = "10.1109/ICMLC.2018.8527032",

language = "English",

isbn = "978-1-5386-5215-2",

volume = "2",

series = "International Conference on Machine Learning and Cybernetics (ICMLC)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "575--580",

booktitle = "Proceedings of the 2018 International Conference on Machine Learning and Cybernetics (ICMLC)",

address = "United States",

note = "2018 International Conference on Machine Learning and Cybernetics, ICMLC 2018 ; Conference date: 15-07-2018 Through 18-07-2018",

}

Chiroma, F, Liu, H & Cocea, M 2018, Suicide related text classification with prism algorithm. in Proceedings of the 2018 International Conference on Machine Learning and Cybernetics (ICMLC). vol. 2, International Conference on Machine Learning and Cybernetics (ICMLC), Institute of Electrical and Electronics Engineers Inc., pp. 575-580, 2018 International Conference on Machine Learning and Cybernetics, Chengdu, China, 15/07/18. https://doi.org/10.1109/ICMLC.2018.8527032

Suicide related text classification with prism algorithm. / Chiroma, Fatima ; Liu, Han; Cocea, Mihaela.
Proceedings of the 2018 International Conference on Machine Learning and Cybernetics (ICMLC). Vol. 2 Institute of Electrical and Electronics Engineers Inc., 2018. p. 575-580 (International Conference on Machine Learning and Cybernetics (ICMLC)).

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

TY - GEN

T1 - Suicide related text classification with prism algorithm

AU - Chiroma, Fatima

AU - Liu, Han

AU - Cocea, Mihaela

PY - 2018/11/12

Y1 - 2018/11/12

N2 - Raw but valuable user data is continuously being generated on social media platforms. This data is, however, more valuable when they are mined using different approaches such as machine learning techniques. Additionally, this user-generated data can be used to potentially save lives especially of vulnerable social media users, as several studies carried out have shown the correlation between social media and suicide. In this study, we aim at contributing to the research relating to suicide communication on social media. We measured the performance of five machine learning algorithms: Prism, Decision Tree, Naive Bayes, Random Forest and Support Vector Machine, in classifying suicide-related text from Twitter. The results of the study showed that the Prism algorithm has outperformed the other machine learning algorithms with an F-measure of 0.84 for the target classes (Suicide and Flippant). This result, to the best of our knowledge, is the highest performance that has been achieved in classifying social media suicide-related text.

AB - Raw but valuable user data is continuously being generated on social media platforms. This data is, however, more valuable when they are mined using different approaches such as machine learning techniques. Additionally, this user-generated data can be used to potentially save lives especially of vulnerable social media users, as several studies carried out have shown the correlation between social media and suicide. In this study, we aim at contributing to the research relating to suicide communication on social media. We measured the performance of five machine learning algorithms: Prism, Decision Tree, Naive Bayes, Random Forest and Support Vector Machine, in classifying suicide-related text from Twitter. The results of the study showed that the Prism algorithm has outperformed the other machine learning algorithms with an F-measure of 0.84 for the target classes (Suicide and Flippant). This result, to the best of our knowledge, is the highest performance that has been achieved in classifying social media suicide-related text.

KW - Text classification

KW - Machine Learning

KW - Prism

KW - Social media

KW - Suicide

UR - http://www.icmlc.com/

UR - https://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000424

U2 - 10.1109/ICMLC.2018.8527032

DO - 10.1109/ICMLC.2018.8527032

M3 - Conference contribution

SN - 978-1-5386-5215-2

VL - 2

T3 - International Conference on Machine Learning and Cybernetics (ICMLC)

SP - 575

EP - 580

BT - Proceedings of the 2018 International Conference on Machine Learning and Cybernetics (ICMLC)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Conference on Machine Learning and Cybernetics

Y2 - 15 July 2018 through 18 July 2018

ER -

Suicide related text classification with prism algorithm

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this