An Indonesian Hoax News Detection System Using Reader Feedback and Naïve Bayes Algorithm

Badrus Zaman; Army Justitia; Kretawiweka Nuraga Sani; Endah Purwanti

doi:10.2478/cait-2020-0006

An Indonesian Hoax News Detection System Using Reader Feedback and Naïve Bayes Algorithm

Badrus Zaman, Army Justitia, Kretawiweka Nuraga Sani, Endah Purwanti

Research output: Contribution to journal › Article › peer-review

22 Citations (Scopus)

Abstract

Hoax news in Indonesia spread at an alarming rate. To reduce this, hoax news detection system needs to be created and put into practice. Such a system may use readers' feedback and Naïve Bayes algorithm, which is used to verify news. Overtime, by using readers' feedback, database corpus will continue to grow and could improve system performance. The current research aims to reach this. System performance evaluation is carried out under two conditions â' with and without sources (URL). The system is able to detect hoax news very well under both conditions. The highest precision, recall and f-measure values when including URL are 0.91, 1, and 0.95 respectively. Meanwhile, the highest value of precision, recall and f-measure without URL are 0.88, 1 and 0.94, respectively.

Original language	English
Pages (from-to)	82-94
Number of pages	13
Journal	Cybernetics and Information Technologies
Volume	20
Issue number	1
DOIs	https://doi.org/10.2478/cait-2020-0006
Publication status	Published - 1 Mar 2020

Keywords

Hoax news
Indonesian news
Naïve Bayes
reader feedback.s

Access to Document

10.2478/cait-2020-0006

Cite this

@article{fe69944fa4f44127b5dccc73f0c80538,

title = "An Indonesian Hoax News Detection System Using Reader Feedback and Na{\"i}ve Bayes Algorithm",

abstract = "Hoax news in Indonesia spread at an alarming rate. To reduce this, hoax news detection system needs to be created and put into practice. Such a system may use readers' feedback and Na{\"i}ve Bayes algorithm, which is used to verify news. Overtime, by using readers' feedback, database corpus will continue to grow and could improve system performance. The current research aims to reach this. System performance evaluation is carried out under two conditions {\^a}' with and without sources (URL). The system is able to detect hoax news very well under both conditions. The highest precision, recall and f-measure values when including URL are 0.91, 1, and 0.95 respectively. Meanwhile, the highest value of precision, recall and f-measure without URL are 0.88, 1 and 0.94, respectively.",

keywords = "Hoax news, Indonesian news, Na{\"i}ve Bayes, reader feedback.s",

author = "Badrus Zaman and Army Justitia and Sani, {Kretawiweka Nuraga} and Endah Purwanti",

note = "Publisher Copyright: {\textcopyright} 2020 Badrus Zaman et al., published by Sciendo.",

year = "2020",

month = mar,

day = "1",

doi = "10.2478/cait-2020-0006",

language = "English",

volume = "20",

pages = "82--94",

journal = "Cybernetics and Information Technologies",

issn = "1311-9702",

publisher = "Institute of Information and Communication Technologies, Bulgarian Academy of Sciences",

number = "1",

}

TY - JOUR

T1 - An Indonesian Hoax News Detection System Using Reader Feedback and Naïve Bayes Algorithm

AU - Zaman, Badrus

AU - Justitia, Army

AU - Sani, Kretawiweka Nuraga

AU - Purwanti, Endah

PY - 2020/3/1

Y1 - 2020/3/1

N2 - Hoax news in Indonesia spread at an alarming rate. To reduce this, hoax news detection system needs to be created and put into practice. Such a system may use readers' feedback and Naïve Bayes algorithm, which is used to verify news. Overtime, by using readers' feedback, database corpus will continue to grow and could improve system performance. The current research aims to reach this. System performance evaluation is carried out under two conditions â' with and without sources (URL). The system is able to detect hoax news very well under both conditions. The highest precision, recall and f-measure values when including URL are 0.91, 1, and 0.95 respectively. Meanwhile, the highest value of precision, recall and f-measure without URL are 0.88, 1 and 0.94, respectively.

AB - Hoax news in Indonesia spread at an alarming rate. To reduce this, hoax news detection system needs to be created and put into practice. Such a system may use readers' feedback and Naïve Bayes algorithm, which is used to verify news. Overtime, by using readers' feedback, database corpus will continue to grow and could improve system performance. The current research aims to reach this. System performance evaluation is carried out under two conditions â' with and without sources (URL). The system is able to detect hoax news very well under both conditions. The highest precision, recall and f-measure values when including URL are 0.91, 1, and 0.95 respectively. Meanwhile, the highest value of precision, recall and f-measure without URL are 0.88, 1 and 0.94, respectively.

KW - Hoax news

KW - Indonesian news

KW - Naïve Bayes

KW - reader feedback.s

UR - http://www.scopus.com/inward/record.url?scp=85083272453&partnerID=8YFLogxK

U2 - 10.2478/cait-2020-0006

DO - 10.2478/cait-2020-0006

M3 - Article

AN - SCOPUS:85083272453

SN - 1311-9702

VL - 20

SP - 82

EP - 94

JO - Cybernetics and Information Technologies

JF - Cybernetics and Information Technologies

IS - 1

ER -

An Indonesian Hoax News Detection System Using Reader Feedback and Naïve Bayes Algorithm

Abstract

Keywords

Access to Document

Fingerprint

Cite this