Abstract

In order to counteract the spread of false information, this study explores the use of machine learning techniques, particularly decision tree classifiers and TF-IDF (Term Frequency-Inverse Document Frequency). Using a dataset of tagged news items, the model is trained to identify patterns that differentiate reliable content from unreliable information.A survey's analysis reveals a worrying trend: fake news has been more common from 2017 to 2018, growing gradually before experiencing a noticeable spike in 2019. But applying current models in 2020 has resulted in a slowdown in the spread of false information.A well-liked machine learning approach called the decision tree classifier provides interpretability by showing decisions as a tree structure. This helps to clarify how the model determines which news is real and which is phony by identifying important characteristics that contribute to the categorization process.In contrast, TF-IDF plays a crucial role in natural language processing tasks by assigning weights to terms according to their significance within a corpus of documents. Through the integration of TF-IDF, the model is able to better identify misinformation by capturing the meaning of words in news stories.All things considered, this study offers a viable strategy to deal with the growing problem of false news by using machine learning techniques and conducting an empirical examination of its effects over time Keywords – Include at least 4 keywords or phrases, must be separated by commas to distinguish them.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call