Exploring the Accuracy of Machine Learning in Detecting Fake News
Nithya Chenthoorani. P1, Mahalakshmi. K2
1Nithya Chenthoorani P, Student, Department of Computer Science and Engineering, Kalaignar Karunanidhi Institute of Technology, Coimbatore (Tamil Nadu), India.
2Mahalaksmi K, Research Supervisor, Department of Computer Science and Engineering, Kalaignar Karunanidhi Institute of Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 27 April 2023 | Revised Manuscript received on 06 May 2023 | Manuscript Accepted on 15 May 2023 | Manuscript published on 30 May 2023 | PP: 44-50 | Volume-12 Issue-6, May 2023 | Retrieval Number: 100.1/ijitee.F95620512623 | DOI: 10.35940/ijitee.F9562.0512623
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Identifying fake news is crucial in the fight against misinformation. To achieve this goal, our project employs SVM and NB algorithms. We also utilize sentiment information from labeled and unlabeled data to improve the sentiment classifiers’ understanding of fake news in each trend. With the proliferation of the internet, there is a growing volume of dubious and intentionally misleading content. The quality of fake news can be so high that it can be challenging to differentiate it from authentic news. Thus, the use of deep learning and machine learning methods for identifying fake news automatically has become significantly crucial. In our project, we pre-process the text using techniques such as stemming, lemmatization and stop word removal from creating text representations for our models. Our system’s essential features are based on two observations: first, we aim to classify words, and second, our customers receive a filtered subset of fake news. To categorize fake news based on the social transmission of false news, we experiment with a simple set of language-independent criteria.
Keywords: SVM, NB, Fake News, Machine Learning, Deep Learning, Stemming, Stop Words, Lemmatization
Scope of the Article: Machine Learning