• M.Sudeepthi
• P.Muthyalu

Fake SMS has a negative impact on individuals and society, Hence the detection of fake SMS is becoming a bigger field of interest for data scientists. Attempts to leverage artificial intelligence technologies particularly machine learning techniques and natural language processing (NLP) to automatically detect fake SMS and prevent its viral spread have recently been actively discussed. Large technology companies have begun to take steps to address this trend. For example, Google has adjusted its SMS rankings to prioritize well- known sites and has banned sites with a history of spreading fake SMS. Facebook has integrated fact checking organizations into its platform. This Project comes up with the applications of NLP (Natural Language Processing) techniques for detecting the 'fake SMS', that is, misleading SMS stories that comes from the non-reputable sources. Detecting and combating the spread of fake news has become increasingly crucial in today's digital age. In this study, we propose a novel approach utilizing Natural Language Processing (NLP) techniques to classify fake news articles. Our method focuses on identifying in-Article Attribution (IAA) as a key feature for distinguishing between legitimate and fake news sources. We employ supervised learning algorithms to train a model capable of accurately categorizing articles based on their attribution characteristics. Through experimentation and evaluation on a diverse dataset, we demonstrate the efficacy of our approach in accurately detecting fake news. Our findings highlight the importance of considering linguistic cues such as in-Article Attribution in the development of robust fake news detection systems. Our methodology involves harnessing a diverse array of NLP techniques to extract and analyse attribution-related characteristics within news articles. These features include the presence of named entities, quotes, citations, and references to external sources, which collectively provide insights into the article's reliability and trustworthiness. By treating the identification of in-Article Attribution as a supervised learning task, we train a machine learning model on a labelled dataset comprising both authentic and fabricated news articles. Through thorough experimentation and evaluation, we establish the efficacy of our approach, ensuring originality and integrity.in accurately classifying articles as either genuine or fake. Our results reveal that incorporating in-Article Attribution features significantly enhances the model's predictive performance, enabling it to discern subtle linguistic cues indicative of misinformation or propaganda. Furthermore, we conduct extensive analyses to elucidate the specific attribution- related patterns and linguistic markers associated with different types of fake news

Fake News Classification, Natural Language Processing (NLP), In-Article Attribution (IAA), Supervised Learning Estimator, Textual Feature Extraction Misinformation Detection, Naïve Bayes

"CLASSIFYING FAKE NEWS ARTICLES USING NATURAL LANGUAGE PROCESSING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.519-525, June-2024, Available :http://www.jetir.org/papers/JETIRGL06086.pdf

"CLASSIFYING FAKE NEWS ARTICLES USING NATURAL LANGUAGE PROCESSING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pp519-525, June-2024, Available at : http://www.jetir.org/papers/JETIRGL06086.pdf