Fake News Detection: An Image-Based Semi-Automated Method Using Statistic Feature

Erick Alfons Lisangan, Astrid Lestari Tungadi, Feri Wibowo

Research output: Chapter in Book/Conference paperConference paperpeer-review

Abstract

The development of information technology has an impact on the speed with which news spreads in the community. From this news, there are some news that are less credible which can cause unrest to propaganda for certain purposes, or so-called fake news. This study designed a semi-automatic method for detecting fake news based on the headline image of the news. The stages of the proposed method are News Crawling and Representation, Feature Extraction, Similarity Measurement, and Source News Recommendation. The crawling process takes advantage of the Bing search engine API. The image features used are the statistical features for each RGB color component, namely the mean, median, and standard deviation. The results showed that the proposed method was able to provide recommendations to users of news sources from fake news headline images. This detection method is expected to help users detect fake news in the form of false context and manipulated content more efficiently.

Original languageEnglish
Title of host publication3rd International Conference on Engineering and Applied Science, InCEAS 2021
EditorsHaryanto Haryanto, Mohammad Mansoob Khan, Setyawan Widyarto, Wakhyu Dwiono, Anwar Ma'ruf, Gatot Rusbintardjo, Anton Yudhana
PublisherAmerican Institute of Physics
Number of pages8
ISBN (Electronic)9780735442337
DOIs
Publication statusPublished - 3 Nov 2022
Externally publishedYes
Event3rd International Conference on Engineering and Applied Science, InCEAS 2021 - Purwokerto, Virtual, Indonesia
Duration: 26 Jul 2021 → …

Publication series

NameAIP Conference Proceedings
Volume2578
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

Conference3rd International Conference on Engineering and Applied Science, InCEAS 2021
Country/TerritoryIndonesia
CityPurwokerto, Virtual
Period26/07/21 → …

Fingerprint

Dive into the research topics of 'Fake News Detection: An Image-Based Semi-Automated Method Using Statistic Feature'. Together they form a unique fingerprint.

Cite this