Deep Learning Techniques for Detection of Fake News in Social Media with Huge Data
M. Namratha, B S Rajeshwari, Jyothi S. Nayak · 2025
The practice of reading news via social media has its pros and cons. Due to media's low cost, ease of use, and quick information transmission, people turn to it for information. However, social media facilitates the widespread dissemination of purposefully misleading information in fake news. Owing to how simple it is to create and distribute information on the internet, the dissemination of false news has recently grown more prevalent. While fake news is not actually true, it is created to appear true for a certain reason. While fake news detection is challenging for humans, deep learning and machine learning methods make the work much simpler. A variety of algorithms for machine learning can make it easier in detecting whether news is true or false. Various researchers utilized classifiers based on machine learning for checking the authenticity of news. It is simple to obtain the datasets needed to train the classifiers. This chapter explains several deep learning method performances combined with the current state-of-the-art word embeddings on benchmark fake news datasets. This chapter mainly focuses on various fake news detection algorithms as mentioned below. To create a thorough study on deep learning models for spotting fake news and the collection of significant information from recent studies along with diverse algorithms employed for achieving it. To present a complete analysis of the chronological review, their related works, and contribution to research designs and general findings on fake news detection models. To analyze the performance metrics, applications, datasets used, simulation platforms used, and necessary research gap along with challenges present in existing fake news detection models.