International Journal of Electrical and Computer Engineering (IJECE) Vol. 15, No. 2, April 2025, pp. 2202~2210 ISSN: 2088-8708, DOI: 10.11591/ijece.v15i2.pp2202-2210  2202 Journal homepage: http://ijece.iaescore.com 4HAN: hypergraph-based hierarchical attention network for fake news prediction Alpana A. Borse 1 , Gajanan. K. Kharate 2 , Namrata G. Kharate 3 1 Department of Computer Engineering, Matoshri College of Engineering and Research Center, Pune University, Maharashtra, India 2 Department of Electronics Engineering, Matoshri College of Engineering and Research Center, Pune University, Maharashtra, India 3 Department of Computer Engineering, Vishwakama Institute of Information Technology, Pune University, Maharashtra, India Article Info ABSTRACT Article history: Received Jul 3, 2024 Revised Nov 29, 2024 Accepted Dec 14, 2024 Fake news presents significant threats to both society and individuals, highlighting the urgent need for improved news authenticity verification. To deal with this challenge, we provide a novel strategy called the 4-level hierarchical attention network (4HAN), designed to enhance fake news detection through an advanced integration of hypergraph convolution and attention neural network mechanisms. The 4HAN model operates across four hierarchical levels: paragraphs, sentences, words, and contextual information (metadata). At the highest level, the model employs hypergraph- based attention and convolution neural networks to create a contextual information vector, utilizing a SoftMax activation function. This vector is then combined with a news content vector generated through word and sentence-level attention mechanisms. This architecture enables the 4HAN model to effectively prioritize the relevance of specific words and contextual information, thereby improving the overall representation and accuracy of news content. We evaluate the 4HAN model using the LIAR dataset to demonstrate its efficacy in enhancing fake news prediction accuracy. Comparative analysis shows that the 4HAN model outperforms several of cutting-edge techniques, like recurrent neural networks (RNN), ensemble techniques, and attention mechanisms techniques. Our results indicate 4HAN model accomplishes a notable accuracy of 96%, showcasing its potential for significantly advancing fake news prediction. Keywords: Attention Classification Fake news Hypergraph Prediction This is an open access article under the CC BY-SA license. Corresponding Author: Alpana Arun Borse Department of Computer Engineering, Matoshri College of Engineering and Research Center, Pune University Eklahare Road, Aurangabad Highway, Nasik District, Maharashtra 42210, India Email: alpana.borse@gmail.com 1. INTRODUCTION In the everyday world, news is essential by keeping the public informed about current events, helping people make informed decisions, and shaping societal opinions. It is essential for understanding the world and participating effectively in civic life. Nowadays, the use of social media is rising as the internet grows [1]; the fake news spread has become more prevalent [1]. This rise is partly due to the ease with which information can be shared and the desire for sensational content. Why is fake news so troubling? Because each of us is influenced by both positive and negative forces [2], it is crucial to have rapid prediction mechanisms to effectively curb the spread of misinformation. Automatic classification [3] of news topics and authenticity of news simultaneously [4] presents a significant challenge and has recently garnered considerable attention from both the public and researchers.