Identifying and Analyzing Extremist Reviewer Groups in Online Product Reviews

A novel approach for identifying and classifying extremist reviewer groups in online product reviews is presented in this paper. The use of machine learning techniques to examine review sentiments and patterns to identify irregularities associated with extremist activity. Feature extraction methods include term frequency-inverse document frequency (TF-IDF) and sentiment analysis with recurrent neural networks (RNN) are part of our methodology. We confirm our detection approach through thorough evaluations employing real-world datasets, demonstrating its efficacy in detecting extremist groups who influence review platforms. The results show how crucial it is to preserve the integrity of online reviews and provide suggestions for possible defenses for e-commerce sites.