INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
The textual data is increasing exponentially in the internet through various social network platforms like discussion Forums, Twitter, Reviews sites, Facebook, Blogs and etc. These platforms changed the method of communication among people. Most of the people are interested to exchange the genuine information in these platforms. Some of them generate false or fake information and spread this information in these platforms. The fake or false information is spreading to defame the reputation of companies, people, services, products, and places. The detection of fake news in people’s communication becomes a popular research area in recent times. Most of the researchers proposed several approaches to detect the fake news or false information by analysing the written text. One way of restricting the spreading of information is when every user checks the truth of news content before spreading news into different social media groups. It is very difficult in this abundant information world to know the correctness of the information. In this context, identification of fake news spreaders is useful for the community of people to recognize whether the textual message came from fake source or genuine source. The PAN competition organizers introduced a task of Fake News Spreaders (FNS) detection in 2020. The task is detecting whether the Twitter author is fake news spreader or not. The organizers provided Twitter dataset for fake news spreaders detection. In this work, we developed a new approach by combining the feature representation methodologies of machine learning techniques and concepts of BERT for features extraction. The documents are represented with the combination of features selected by the feature selection algorithm and the documents representation by the BERT model. Support Vector Machine (SVM) classifier is used for evaluating the efficiency of the proposed approach. The SVM classifier with combined vector representation shows best accuracy for fake news spreaders detection.
"A Combined Machine Learning and Deep Learning Techniques based Approach for Fake News Spreaders Detection ", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.7, Issue 12, page no.a245-a253, December-2022, Available :http://www.ijnrd.org/papers/IJNRD2212036.pdf
Downloads:
000118750
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn