Copyright © 2025 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{167294,
        author = {RAMYA MEDI and N.NAVEEN KUMAR},
        title = {EVERLASTING RUMOR DETECTION FRAMEWORK},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {883-888},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167294},
        abstract = {— In this study, we address the challenge of rumor
detection on Weibo and Twitter, where training data is
limited and news updates rapidly. Leveraging Lifelong
Machine Learning (LML), we propose a novel approach to
continuously learn and accumulate knowledge for
improved detection performance. We explore various
models including BERT GCN, Bi-GCN, RvNN, Naive
Bayes, Decision Tree, SVM-RBF, SVM-TK, and Voting
Classifier. Evaluating these models on Weibo and Twitter
datasets, we observe significant performance variations.
BiGCN achieves 90% accuracy, while BERT GCN with
LSTM and CNN, LSTM, LSTM + GRU, and Voting
Classifier attain 93%, 99%, 95%, and 97% accuracy,
respectively. These results underscore the effectiveness of
lifelong learning paradigms in enhancing rumor detection
in dynamic online environments. Our findings highlight
the potential of leveraging diverse algorithms in
conjunction with LML for robust and accurate rumor
detection in social media platforms.},
        keywords = {Lifelong machine learning, continuous
learning, Weibo rumor, the best minimum feature.},
        month = {August},
        }