ERS – GARNET: An Ensemble Recommendation System for Sentiment Analysis Using Gated Attention-Based Recurrent Networks

Sentiment analysis (SA), the process of determining the emotional tone behind a piece of text, has gained significant importance in various domains, including marketing, customer feedback analysis, and social media monitoring. Traditional SA models often face challenges handling diverse global datasets due to language variations, cultural nuances, and context differences. This paper proposes an Ensemble Recommendation System (ERS) approach to address these challenges and improve SA accuracy. The ERS combines Gated Attention-Based Recurrent Networks (GARNET) Steps with Transfer Learning. The ERS leverages the power of ensemble learning, combining multiple sentiment analysis models trained on global datasets from diverse linguistic backgrounds. The ERS can provide more robust and accurate sentiment classifications by aggregating predictions from these models. Additionally, the system utilizes a recommendation mechanism that dynamically selects the most suitable model based on the characteristics of the input text, such as language, tone, and context. In this paper, an advanced pre-trained model DistilBERT is used to train the selected datasets and apply transfer learning. Transfer learning is used to send the features extracted from training and sends them to the proposed approach ERS. Second, we design and train multiple state-of-the-art SA models integrated to handle specific linguistic attributes while also considering the cultural biases present in the datasets. Third, we introduce the ERS recommendation mechanism, which enhances the system's performance and optimizes computational resources. For the effectiveness of the proposed ERS, extensive experiments were conducted on benchmark datasets and comparing its performance with individual sentiment analysis models and conventional ensemble techniques. The performance of the proposed approach achieves superior sentiment classification accuracy, especially when dealing with challenging global datasets. Finally, ERS presents a promising solution for deep sentiment analysis over diverse global datasets. Finally, the ERS also focused on finding the popular items or products recommended by the proposed approach.