Issuu

International Research Journal of Engineering and Technology (IRJET) Volume: 12 Issue: 11 | Nov 2025 www.irjet.net

e-ISSN: 2395-0056 p-ISSN: 2395-0072

Fake News Detection Using NLP Sasirekha C1 , Bhuvaneshwari B2 1PG Student, Department Of Computer Applications, Jaya College Of Arts and Science, Thiruninravur,

Tamilnadu,India

2Assistant Professor, Department Of Computer Applications, Jaya College Of Arts and Science, Thiruninravur,

Tamilnadu,India ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract – Fake news has become a significant problem in 2.LITERATURE REVIEW today’s digital era, where information spreads rapidly across social media and online platforms. The dissemination of false or misleading news can manipulate public perception, create confusion, and even impact social, political, and economic stability. To address this challenge, Natural Language Processing (NLP) techniques are widely used to automatically detect and classify fake news based on textual content. By applying methods such as text preprocessing, feature extraction, and machine learning or deep learning algorithms, NLP enables computers to understand linguistic cues and semantic patterns within news articles. This study focuses on developing an NLPbased fake news detection system that analyzes the language structure and context of news to differentiate between authentic and deceptive information. The approach aims to improve accuracy and reliability in detecting misinformation, contributing to a safer and more trustworthy digital information environment.

Fake news detection has become an important research area in recent years due to the rapid spread of misinformation through social media and online news platforms. Researchers have explored various Natural Language Processing (NLP) and Machine Learning (ML) techniques to automatically identify deceptive news content. According to Shu et al. (2017), fake news can be analyzed from three main perspectives — news content, social context, and propagation patterns — and combining these factors enhances detection accuracy. Early studies primarily focused on content-based detection using textual features such as word frequency, part-of-speech tags, and readability scores. Classical algorithms like Naive Bayes, Logistic Regression, and Support Vector Machines were widely used for classification tasks (Horne & Adalı, 2017). With the availability of benchmark datasets like LIAR (Wang, 2017) and FakeNewsNet (Shu et al., 2018), researchers gained access to large-scale labeled data for training and testing models. These datasets enabled the development of both traditional and deep learning-based approaches. In recent years, deep learning models such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), particularly LSTMs, have been effectively used to capture semantic and contextual relationships in text, improving detection accuracy. The introduction of transformer-based models such as BERT (Devlin et al., 2018) further revolutionized fake news detection by providing rich contextual embeddings and reducing the need for manual feature engineering.

Keywords: Fake News Detection, Natural Language Processing (NLP), Machine Learning,Text Classification, News Authenticity, Data Mining

1.INTRODUCTION In the digital age, the rapid spread of information through social media and online platforms has made it easier for fake news to circulate widely, influencing public opinion and decision-making. Fake news refers to false or misleading information presented as legitimate news, often created to deceive readers or promote specific agendas. Detecting such misinformation has become a major challenge due to the vast amount of data generated daily. Natural Language Processing (NLP), a branch of Artificial Intelligence (AI), plays a crucial role in addressing this issue by enabling machines to understand, analyze, and interpret human language. Through techniques such as text classification, sentiment analysis, and semantic understanding, NLP helps identify linguistic patterns and inconsistencies that distinguish fake news from real news. Combining NLP with machine learning and deep learning algorithms has significantly improved the accuracy and efficiency of fake news detection systems. As a result, NLP-based approaches have become an essential tool in combating misinformation and maintaining the credibility of online information sources.

Impact Factor value: 8.315

3.METHODOLOGY The methodology for Fake News Detection using Natural Language Processing (NLP) generally involves several systematic stages to process textual data, extract meaningful features, and classify news content as real or fake. The process typically begins with data

3.1Existing System The Existing systems for fake news detection, traditional machine learning approaches are mainly used, which rely heavily on manual feature engineering. These systems typically utilize datasets of news articles labeled as “fake”

ISO 9001:2008 Certified Journal

Page 282