Abstract: The field of Natural Language Processing (NLP) has gained significant attention in recent years, particularly in the context of fake news detection and categorization. NLP techniques offer powerful tools to analyse and understand textual data, allowing us to identify patterns, sentiments, and linguistic features that can help distinguish between true and false news. In this project, we aim to predict false news and determine their respective categories using NLP techniques. To achieve this, we will employ a combination of supervised machine learning algorithms and NLP methods. Firstly, we will gather a dataset consisting of news articles labelled as either true or false. The dataset will also include information regarding the category or topic of each news article. These categories may range from politics and sports to entertainment and science. Next, we will pre-process the textual data by performing tasks such as tokenization, stop-word removal, and stemming. These steps will help to clean and transform the raw text into a format suitable for analysis.
Keywords: False news prediction, news categorization, NLP techniques, supervised machine learning, textual data, tokenization, stop-word removal, stemming, TF-IDF, word embedding’s, logistic regression, random forests, support vector machines.
Works Cited:
G. Agasthiya, Mrs. S. Jancy Sickory Daisy " FAKE NEWS DETECTION USING NLP", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 12, no. 9, pp. 53-60, 2023. Crossref https://doi.org/10.17148/IJARCCE.2023.12907
|
DOI:
10.17148/IJARCCE.2023.12907
