UPM Institutional Repository

SVM-based approach for detecting misleading online news articles


Che Eembi @ Jamil, Normala and Ishak, Iskandar and Sidi, Fatimah and Affendey, Lilly Suriani (2019) SVM-based approach for detecting misleading online news articles. In: International Symposium on ICT Management and Administration (ISICTMA2019), 31 July-2 Aug. 2019, Putrajaya Marriott Hotel, Malaysia. (pp. 51-54).


Since its existence in the 1990s, online news has been the primary source of news content for newsreaders. Unfortunately, based on several findings, readers tend to judge on specific event based on the news headlines rather than its contents. With the advancement of mobile and web technologies, it is easier to spread the news to others through this medium habits that can cause negative impacts towards individuals, organizations, or nations that are victimized by the news. Therefore, it is an important task to determine the truth about information being spread to the public, such as online news. To solve this problem, multiple methods have been developed to detect misleading online news. In this works, we aim to improve deception detection method on online news based by simplifying the pre-processing and improve features selection techniques to improve the SVM-based deception detection approach accuracy. The experimental results showed that the proposed approach managed to improve the efficiency above 90%.

Download File

[img] Text
Restricted to Repository staff only

Download (415kB)

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Computer Science and Information Technology
Publisher: Database Technologies and Applications Research Group (DbTA), Faculty of Computer Science and Information Technology, Universiti Putra Malaysia
Keywords: Veracity; Deception; Truthfulness; Accuracy; Headline; Content; Online news
Depositing User: Nabilah Mustapa
Date Deposited: 07 Oct 2019 07:39
Last Modified: 14 Oct 2019 08:03
URI: http://psasir.upm.edu.my/id/eprint/75521
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item