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{206751,
        author = {Dhanyashree and Aparna N and Prathibha and Deeksha and Nisha},
        title = {Fake News Detection using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {309-314},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206751},
        abstract = {The world of digital media is increasing at a very rapid pace in Recent Years. Due to this, too much fake news is also being created. It is a serious problem that is becoming one of the greatest threats of the world. It alters the thinking of people and creates misunderstanding. Additionally, it causes numerous misunderstandings or befuddlement. In addition to this, it also has social and political effects. Though many people read the news properly, some don’t. It is becoming hard to contain fake news because of this. For building a fake news detector, we are using the model building method of machine learning. We will be able to recognize valid news and fake news with the help of this. Initially, data collection was done by us. The cleaning process was performed afterward. In this step, we did the tokenization, removal of stop words and normalisation. At first, these are important but little confusing. Then, we used TF-IDF to change the text into numbers. The model can't understand the text, so we convert all the text to numbers. Subsequently, algorithms such as Logistic Regression, Passive-Aggressive Classifier, Naïve Bayes, and SVM were utilized. Some models yield better results than others do. We have built a web application using Flask. Users can input the news text and acquire the outcome in this. It is not complicated, easy to use. For performance, we use accuracy and Precision and recall and F1 score. This model is correct up to 99%. It could have a bit of error sometimes, but overall, it is pretty much correct. The method to detect the false information includes machine learning and NLP for feature extraction and classification of the text. Passive aggressive classifier, TF-IDF vectorization.},
        keywords = {False news detection, feature extraction, machine learning, natural language processing, passive aggressive classifier, text classification, TF-IDF vectorization.},
        month = {July},
        }