International Research Journal of Engineering and Technology (IRJET) Volume: 11 Issue: 04 | Apr 2024
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
Fake News Detection Using Machine Learning Tridib Khute1, Bhupendra Kumar Kumbhkar2, Mrinal Pawar3, Priyanka Devi4 1B.Tech Student, Dept. of Information Technology, Govt. Engineering college Bilaspur, C.G, India 2B.Tech Student, Dept. of Information Technology, Govt. Engineering. college Bilaspur, C.G, India 3B.Tech Student, Dept. of Information Technology, Govt. Engineering college Bilaspur, C.G, India
4Assistant Professor, Dept. of Information Technology, Govt. Engineering college Bilaspur, C.G, India
------------------------------------------------------------***-----------------------------------------------------------
Abstract - Fake information has emerge as a pervasive
numerous mediums, such as social media platforms, news web sites, and different online resources. Fake news often aims to control public opinion, unfold propaganda, or generate clickbait for financial advantage. It may additionally contain fabricated memories, distorted records, or misattributed resources, in the long run undermining the credibility of dependable journalism and posing widespread challenges to the integrity of statistics ecosystems."
problem in today’s virtual age, posing substantial demanding situations to statistics integrity and public discourse. This paper examines the usage of device getting to know to come across fake news. The research makes a speciality of growing and trying out system gaining knowledge of algorithms that could distinguish among credible information assets and fraudulent facts. The review begins with a comprehensive review of the existing literature on link detection, highlighting limitations and gaps in current methodologies. Data types including real and synthetic media are collected and preprocessed to extract relevant features including textual content, metadata, and language samples Using various machine learning algorithms such as logistic regression, random forest, and neural networks are used and compared for better performance in classifying false information Analytical metrics such as accuracy, precision, recall, and F1 score are used to evaluate the performance of machine learning models. Significant factor analysis is performed to identify key determinants of false positives, which contribute to the interpretation of the model. The research also explores cluster learning methods and sample clustering strategies to further enhance classification accuracy and robustness. The research results show promising results in the detection of fake news, showing the ability of machine learning to deal with misinformation The findings contribute to the advancement of fake news detection technology, and inform news organisations, social media channels and law enforcement agencies gain valuable insights for addressing the fake news epidemic.
1.1 Importance of Fake News Detection Preserving Information Integrity: With the rapid dissemination of information facilitated by digital platforms, the prevalence of fake news poses a threat to the integrity of information ecosystems. Mitigating Social and Political Impacts: False information propagated through fake news can have far-reaching consequences on social and political landscapes, including electoral processes, public policy decisions, and community cohesion. Enhancing Media Literacy: Fake news prediction research contributes to the development of tools and methodologies for enhancing media literacy among users. Supporting Fact-Checking Efforts: Predicting fake news complements the efforts of factchecking organisations and journalists in verifying the accuracy of information. Machine learning algorithms can assist in the automated identification of potentially false or misleading claims, thereby expediting the factchecking process and enabling more timely corrections and retractions. Finally, the fake news detection is very helpful and important in this virtual age.
Key Words: Machine Learning, Natural Language Processing, Fake news, Data Preprocessing, Logistic Regression, Random Forest, Decision Tree Classifier.
1.2 Role of Machine Learning in Fake News Detection Machine learning makes it easy to extract relevant features from news content, metadata, and context. Considering different aspects of the data, including linguistic characteristics, such as vocabulary and style, social characteristics such as user engagement and distribution, and source credibility considerations a, machine learning models can better distinguish between true and fake news. Machine learning provides flexibility and scalability, allowing false alarm prediction
1.INTRODUCTION For the purpose of the research paper on fake news prediction the use of machine getting to know, we are able to define fake news as: "Fake news refers to intentionally false or deceptive information offered as legitimate news.[1] This misinformation can be created and disseminated via
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 985