Classification of Toxic Comments on Social Networks Using Machine Learning

María Fernanda Revelo-Bautista; Jair Oswaldo Bedoya-Benavides; Jaime Paúl Sayago-Heredia; Pablo Pico-Valencia; Xavier Quiñonez-Ku

doi:10.1007/978-3-031-58953-9_20

Classification of Toxic Comments on Social Networks Using Machine Learning

María Fernanda Revelo-Bautista, Jair Oswaldo Bedoya-Benavides, Jaime Paúl Sayago-Heredia, Pablo Pico-Valencia, Xavier Quiñonez-Ku

PUCE Esmeraldas

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

Abstract

This research addresses the problem of toxic comments in social networks, and how artificial intelligence (AI) and machine learning (Machine Learning) can help. It presents the development of a classification model using AI with machine learning techniques to identify toxic comments on Twitter. The proposed classifier, developed in Python, was established with 7 different algorithms using approaches or strategies for multi-label classification, preprocessing, cleaning and data visualization. This model was trained with a total of 159571 comments from the Kaggle repository dataset called Jigsaw, which has the comments classified with various features. After the training, evaluation and comparison of the model created, the result was a classifier capable of identifying toxic and offensive words or comments with an accuracy of 92.16%.

Original language	English
Title of host publication	International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers
Editors	Miguel Botto-Tobar, Marcelo Zambrano Vizuete, Sergio Montes León, Pablo Torres-Carrión, Benjamin Durakovic
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	257-270
Number of pages	14
ISBN (Print)	9783031589522
DOIs	https://doi.org/10.1007/978-3-031-58953-9_20
State	Published - 2024
Event	5th International Conference on Applied Technologies, ICAT 2023 - Samborondon, Ecuador Duration: 22 Nov 2023 → 24 Nov 2023

Publication series

Name	Communications in Computer and Information Science
Volume	2050 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	5th International Conference on Applied Technologies, ICAT 2023
Country/Territory	Ecuador
City	Samborondon
Period	22/11/23 → 24/11/23

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Keywords

machine learning
sentiment analysis
text classification
toxic comments
tweets
twitter

Access to Document

10.1007/978-3-031-58953-9_20

Cite this

Revelo-Bautista, M. F., Bedoya-Benavides, J. O., Sayago-Heredia, J. P., Pico-Valencia, P., & Quiñonez-Ku, X. (2024). Classification of Toxic Comments on Social Networks Using Machine Learning. In M. Botto-Tobar, M. Zambrano Vizuete, S. Montes León, P. Torres-Carrión, & B. Durakovic (Eds.), International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers (pp. 257-270). (Communications in Computer and Information Science; Vol. 2050 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-58953-9_20

Revelo-Bautista, María Fernanda ; Bedoya-Benavides, Jair Oswaldo ; Sayago-Heredia, Jaime Paúl et al. / Classification of Toxic Comments on Social Networks Using Machine Learning. International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers. editor / Miguel Botto-Tobar ; Marcelo Zambrano Vizuete ; Sergio Montes León ; Pablo Torres-Carrión ; Benjamin Durakovic. Springer Science and Business Media Deutschland GmbH, 2024. pp. 257-270 (Communications in Computer and Information Science).

@inproceedings{dfe3a11f4c7e4b878511119052eef22c,

title = "Classification of Toxic Comments on Social Networks Using Machine Learning",

abstract = "This research addresses the problem of toxic comments in social networks, and how artificial intelligence (AI) and machine learning (Machine Learning) can help. It presents the development of a classification model using AI with machine learning techniques to identify toxic comments on Twitter. The proposed classifier, developed in Python, was established with 7 different algorithms using approaches or strategies for multi-label classification, preprocessing, cleaning and data visualization. This model was trained with a total of 159571 comments from the Kaggle repository dataset called Jigsaw, which has the comments classified with various features. After the training, evaluation and comparison of the model created, the result was a classifier capable of identifying toxic and offensive words or comments with an accuracy of 92.16%.",

keywords = "machine learning, sentiment analysis, text classification, toxic comments, tweets, twitter",

author = "Revelo-Bautista, {Mar{\'i}a Fernanda} and Bedoya-Benavides, {Jair Oswaldo} and Sayago-Heredia, {Jaime Pa{\'u}l} and Pablo Pico-Valencia and Xavier Qui{\~n}onez-Ku",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; 5th International Conference on Applied Technologies, ICAT 2023 ; Conference date: 22-11-2023 Through 24-11-2023",

year = "2024",

doi = "10.1007/978-3-031-58953-9_20",

language = "English",

isbn = "9783031589522",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "257--270",

editor = "Miguel Botto-Tobar and {Zambrano Vizuete}, Marcelo and {Montes Le{\'o}n}, Sergio and Pablo Torres-Carri{\'o}n and Benjamin Durakovic",

booktitle = "International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers",

}

Revelo-Bautista, MF, Bedoya-Benavides, JO, Sayago-Heredia, JP , Pico-Valencia, P & Quiñonez-Ku, X 2024, Classification of Toxic Comments on Social Networks Using Machine Learning. in M Botto-Tobar, M Zambrano Vizuete, S Montes León, P Torres-Carrión & B Durakovic (eds), International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers. Communications in Computer and Information Science, vol. 2050 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 257-270, 5th International Conference on Applied Technologies, ICAT 2023, Samborondon, Ecuador, 22/11/23. https://doi.org/10.1007/978-3-031-58953-9_20

Classification of Toxic Comments on Social Networks Using Machine Learning. / Revelo-Bautista, María Fernanda; Bedoya-Benavides, Jair Oswaldo; Sayago-Heredia, Jaime Paúl et al.
International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers. ed. / Miguel Botto-Tobar; Marcelo Zambrano Vizuete; Sergio Montes León; Pablo Torres-Carrión; Benjamin Durakovic. Springer Science and Business Media Deutschland GmbH, 2024. p. 257-270 (Communications in Computer and Information Science; Vol. 2050 CCIS).

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

TY - GEN

T1 - Classification of Toxic Comments on Social Networks Using Machine Learning

AU - Revelo-Bautista, María Fernanda

AU - Bedoya-Benavides, Jair Oswaldo

AU - Sayago-Heredia, Jaime Paúl

AU - Pico-Valencia, Pablo

AU - Quiñonez-Ku, Xavier

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024

Y1 - 2024

N2 - This research addresses the problem of toxic comments in social networks, and how artificial intelligence (AI) and machine learning (Machine Learning) can help. It presents the development of a classification model using AI with machine learning techniques to identify toxic comments on Twitter. The proposed classifier, developed in Python, was established with 7 different algorithms using approaches or strategies for multi-label classification, preprocessing, cleaning and data visualization. This model was trained with a total of 159571 comments from the Kaggle repository dataset called Jigsaw, which has the comments classified with various features. After the training, evaluation and comparison of the model created, the result was a classifier capable of identifying toxic and offensive words or comments with an accuracy of 92.16%.

AB - This research addresses the problem of toxic comments in social networks, and how artificial intelligence (AI) and machine learning (Machine Learning) can help. It presents the development of a classification model using AI with machine learning techniques to identify toxic comments on Twitter. The proposed classifier, developed in Python, was established with 7 different algorithms using approaches or strategies for multi-label classification, preprocessing, cleaning and data visualization. This model was trained with a total of 159571 comments from the Kaggle repository dataset called Jigsaw, which has the comments classified with various features. After the training, evaluation and comparison of the model created, the result was a classifier capable of identifying toxic and offensive words or comments with an accuracy of 92.16%.

KW - machine learning

KW - sentiment analysis

KW - text classification

KW - toxic comments

KW - tweets

KW - twitter

UR - http://www.scopus.com/inward/record.url?scp=85196098500&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-58953-9_20

DO - 10.1007/978-3-031-58953-9_20

M3 - Conference contribution

AN - SCOPUS:85196098500

SN - 9783031589522

T3 - Communications in Computer and Information Science

SP - 257

EP - 270

BT - International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers

A2 - Botto-Tobar, Miguel

A2 - Zambrano Vizuete, Marcelo

A2 - Montes León, Sergio

A2 - Torres-Carrión, Pablo

A2 - Durakovic, Benjamin

PB - Springer Science and Business Media Deutschland GmbH

T2 - 5th International Conference on Applied Technologies, ICAT 2023

Y2 - 22 November 2023 through 24 November 2023

ER -

Revelo-Bautista MF, Bedoya-Benavides JO, Sayago-Heredia JP , Pico-Valencia P , Quiñonez-Ku X. Classification of Toxic Comments on Social Networks Using Machine Learning. In Botto-Tobar M, Zambrano Vizuete M, Montes León S, Torres-Carrión P, Durakovic B, editors, International Conference on Applied Technologies - 5th International Conference on Applied Technologies, ICAT 2023, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2024. p. 257-270. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-58953-9_20

Classification of Toxic Comments on Social Networks Using Machine Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Cite this