Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184988,
        author = {Chayana Rajput and Ankit Garg},
        title = {Predicting Rumors in Social Media Using RNN and NLP},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {4248-4256},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184988},
        abstract = {The spread of rumors is quickly becoming one of the most significant issues that sectors and the business world face today. It is possible for pervasive dissemination of false information to have devastating consequences, not only for individuals but also for society as a whole. The objective of disseminating false information via rumors is to deceive audience into believing that it is true. Due to this, identifying rumors based on the content of individual articles can be difficult and time-consuming. In this paper, we propose a technique for predicting rumors in social media using RNN and NLP to circumvent this issue. Initially, datasets are collected from publicly accessible sources. After the data has been collected, the pre-processing stages are executed, which include text normalization, lemmatization, and the removal of stop words. Tokenization is the reduction of a sentence or paragraph into its constituent terms. Word embedding is achieved through the use of POS, a procedure that entails assigning a tag to each word. Recurrent Neural Networks (RNN) used to classify the data. Finally, it has been determined whether the news was genuine or a rumor the entire time. The results indicate, the proposed strategy performs well when compared to the performance of alternative deep learning strategies.},
        keywords = {Deep Learning, Fake News Classification, Information Verification, Lemmatization, Natural Language Processing (NLP), Recurrent Neural Network (RNN).},
        month = {September},
        }