Deep recurrent neural network‐based Aquila optimization‐based online shaming emotion analysis
B. Aarthi, Balika J Chelliah · Concurrency and Computation Practice and Experience · 2022
Abstract Thanks to the emergence of social media and internet platforms, people currently have a plethora of possibilities for openly expressing their thoughts. As a result, it provides millions of ways to create intelligent systems; yet, some people take advantage of these platforms by insulting, harassing, or abusing others. As a result, emotional analysis of online shaming is necessary for avoiding the attackers' negative consequences. In this field, several studies are conducted to classify shaming and non‐shaming comments in order to identify shamers. The optimum classification, on the other hand, has yet to be established. As a result, we introduced a novel deep learning approach known as deep recurrent neural network based classifier, which categorizes the comments. Based on the category. To improve classification accuracy, we used the Aquila optimization algorithm, which improves shaming classification based on category. The experimental analysis is carried out by determining some performance indicators and comparing them to other existing works. The performance analysis reveals that the proposed method outperforms all other approaches.