A comparative study of machine learning algorithms and text vectorization methods for fake news detection

Andreas Kanavos; Ioannis Karamitsos; Alaa Mohasseb; Vassilis Gerogiannis

doi:10.1109/IISA59645.2023.10345953

A comparative study of machine learning algorithms and text vectorization methods for fake news detection

Andreas Kanavos, Ioannis Karamitsos, Alaa Mohasseb, Vassilis Gerogiannis

School of Computing

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

45 Downloads (Pure)

Abstract

The detection of fake news is a crucial task in today's society, given the widespread use of social media and online platforms. In this study, we investigate the application of Machine Learning (ML) algorithms for the detection of fake news. We consider two different datasets of categorized news articles of various sizes and apply various ML algorithms, along with two methods of text vectorization. Specifically, we examine Bag of Words and Tf-Idf, with the use of stemming and with different n-gram values. The resulting vectors are processed by Naive Bayes algorithms, Linear algorithms, Support Vector Machines, and Random Forest Classifiers. F1-Score and computational time for each algorithm-vectorization combination were recorded. Our results have shown that Linear Algorithms and Support Vector Machines combined with Tf-Idf vectors and n-gram value of (1,2) produced the highest accuracies, with an F1-Score up to 96.8%.

Original language	English
Title of host publication	Proceedings of the 14th International Conference on Information, Intelligence, Systems and Applications (IISA2023)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	8
ISBN (Electronic)	9798350318067
ISBN (Print)	9798350318074
DOIs	https://doi.org/10.1109/IISA59645.2023.10345953
Publication status	Published - 15 Dec 2023
Event	14th International Conference on Information, Intelligence, Systems and Applications - University of Thessaly, Volos, Greece Duration: 10 Jul 2023 → 12 Jul 2023 Conference number: 14 https://easyconferences.eu/iisa2023/

Conference

Conference	14th International Conference on Information, Intelligence, Systems and Applications
Abbreviated title	IISA 2023
Country/Territory	Greece
City	Volos
Period	10/07/23 → 12/07/23
Internet address	https://easyconferences.eu/iisa2023/

Keywords

Machine Learning
Text Mining
Information Retrieval
Fake News Detection

Access to Document

10.1109/IISA59645.2023.10345953

IISA_Comparative_Study_of_Machine_Learning_Algorithms_and_Text_Vectorization_Methods_for_Fake_News_Detection
© © 2023 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), 208 KB

Cite this

Kanavos, A., Karamitsos, I., Mohasseb, A., & Gerogiannis, V. (2023). A comparative study of machine learning algorithms and text vectorization methods for fake news detection. In Proceedings of the 14th International Conference on Information, Intelligence, Systems and Applications (IISA2023) Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IISA59645.2023.10345953

@inproceedings{76b7d5173beb48d8abb733839f43add6,

title = "A comparative study of machine learning algorithms and text vectorization methods for fake news detection",

abstract = "The detection of fake news is a crucial task in today's society, given the widespread use of social media and online platforms. In this study, we investigate the application of Machine Learning (ML) algorithms for the detection of fake news. We consider two different datasets of categorized news articles of various sizes and apply various ML algorithms, along with two methods of text vectorization. Specifically, we examine Bag of Words and Tf-Idf, with the use of stemming and with different n-gram values. The resulting vectors are processed by Naive Bayes algorithms, Linear algorithms, Support Vector Machines, and Random Forest Classifiers. F1-Score and computational time for each algorithm-vectorization combination were recorded. Our results have shown that Linear Algorithms and Support Vector Machines combined with Tf-Idf vectors and n-gram value of (1,2) produced the highest accuracies, with an F1-Score up to 96.8%.",

keywords = "Machine Learning, Text Mining, Information Retrieval, Fake News Detection",

author = "Andreas Kanavos and Ioannis Karamitsos and Alaa Mohasseb and Vassilis Gerogiannis",

note = "No embargo. {\textcopyright} 20xx 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.; 14th International Conference on Information, Intelligence, Systems and Applications, IISA 2023 ; Conference date: 10-07-2023 Through 12-07-2023",

year = "2023",

month = dec,

day = "15",

doi = "10.1109/IISA59645.2023.10345953",

language = "English",

isbn = "9798350318074",

booktitle = "Proceedings of the 14th International Conference on Information, Intelligence, Systems and Applications (IISA2023)",

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

address = "United States",

url = "https://easyconferences.eu/iisa2023/",

}

Kanavos, A, Karamitsos, I, Mohasseb, A & Gerogiannis, V 2023, A comparative study of machine learning algorithms and text vectorization methods for fake news detection. in Proceedings of the 14th International Conference on Information, Intelligence, Systems and Applications (IISA2023). Institute of Electrical and Electronics Engineers Inc., 14th International Conference on Information, Intelligence, Systems and Applications, Volos, Greece, 10/07/23. https://doi.org/10.1109/IISA59645.2023.10345953

A comparative study of machine learning algorithms and text vectorization methods for fake news detection. / Kanavos, Andreas; Karamitsos, Ioannis; Mohasseb, Alaa et al.
Proceedings of the 14th International Conference on Information, Intelligence, Systems and Applications (IISA2023). Institute of Electrical and Electronics Engineers Inc., 2023.

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

TY - GEN

T1 - A comparative study of machine learning algorithms and text vectorization methods for fake news detection

AU - Kanavos, Andreas

AU - Karamitsos, Ioannis

AU - Mohasseb, Alaa

AU - Gerogiannis, Vassilis

N1 - Conference code: 14

PY - 2023/12/15

Y1 - 2023/12/15

N2 - The detection of fake news is a crucial task in today's society, given the widespread use of social media and online platforms. In this study, we investigate the application of Machine Learning (ML) algorithms for the detection of fake news. We consider two different datasets of categorized news articles of various sizes and apply various ML algorithms, along with two methods of text vectorization. Specifically, we examine Bag of Words and Tf-Idf, with the use of stemming and with different n-gram values. The resulting vectors are processed by Naive Bayes algorithms, Linear algorithms, Support Vector Machines, and Random Forest Classifiers. F1-Score and computational time for each algorithm-vectorization combination were recorded. Our results have shown that Linear Algorithms and Support Vector Machines combined with Tf-Idf vectors and n-gram value of (1,2) produced the highest accuracies, with an F1-Score up to 96.8%.

AB - The detection of fake news is a crucial task in today's society, given the widespread use of social media and online platforms. In this study, we investigate the application of Machine Learning (ML) algorithms for the detection of fake news. We consider two different datasets of categorized news articles of various sizes and apply various ML algorithms, along with two methods of text vectorization. Specifically, we examine Bag of Words and Tf-Idf, with the use of stemming and with different n-gram values. The resulting vectors are processed by Naive Bayes algorithms, Linear algorithms, Support Vector Machines, and Random Forest Classifiers. F1-Score and computational time for each algorithm-vectorization combination were recorded. Our results have shown that Linear Algorithms and Support Vector Machines combined with Tf-Idf vectors and n-gram value of (1,2) produced the highest accuracies, with an F1-Score up to 96.8%.

KW - Machine Learning

KW - Text Mining

KW - Information Retrieval

KW - Fake News Detection

U2 - 10.1109/IISA59645.2023.10345953

DO - 10.1109/IISA59645.2023.10345953

M3 - Conference contribution

SN - 9798350318074

BT - Proceedings of the 14th International Conference on Information, Intelligence, Systems and Applications (IISA2023)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th International Conference on Information, Intelligence, Systems and Applications

Y2 - 10 July 2023 through 12 July 2023

ER -

Kanavos A, Karamitsos I, Mohasseb A, Gerogiannis V. A comparative study of machine learning algorithms and text vectorization methods for fake news detection. In Proceedings of the 14th International Conference on Information, Intelligence, Systems and Applications (IISA2023). Institute of Electrical and Electronics Engineers Inc. 2023 doi: 10.1109/IISA59645.2023.10345953