🤖 AI Summary
Existing lexicon-based and traditional machine learning approaches for sentiment analysis suffer from limited contextual modeling capability, poor generalization, and inadequate handling of class imbalance—particularly for negative sentiment. To address these challenges, this paper proposes a hybrid deep neural network architecture integrating Bidirectional Gated Recurrent Units (BGRU) and Long Short-Term Memory (LSTM) networks. The model jointly captures long-range dependencies and bidirectional semantic context, thereby significantly enhancing negative sentiment detection. Evaluations on the IMDB and Amazon review datasets demonstrate a test accuracy of 95%, a negative sentiment recall rate of 96%, and a reduction in misclassification loss from 20.24% to 13.3%. Compared to state-of-the-art methods, the proposed model achieves superior performance in accuracy, robustness, and class-balanced prediction, making it especially suitable for fine-grained opinion mining in social media and e-commerce applications.
📝 Abstract
Understanding customer attitudes has become a critical component of decision-making due to the growing influence of social media and e-commerce. Text-based opinions are the most structured, hence playing an important role in sentiment analysis. Most of the existing methods, which include lexicon-based approaches and traditional machine learning techniques, are insufficient for handling contextual nuances and scalability. While the latter has limitations in model performance and generalization, deep learning (DL) has achieved improvement, especially on semantic relationship capturing with recurrent neural networks (RNNs) and convolutional neural networks (CNNs). The aim of the study is to enhance opinion mining by introducing a hybrid deep neural network model that combines a bidirectional gated recurrent unit (BGRU) and long short-term memory (LSTM) layers to improve sentiment analysis, particularly addressing challenges such as contextual nuance, scalability, and class imbalance. To substantiate the efficacy of the proposed model, we conducted comprehensive experiments utilizing benchmark datasets, encompassing IMDB movie critiques and Amazon product evaluations. The introduced hybrid BGRU-LSTM (HBGRU-LSTM) architecture attained a testing accuracy of 95%, exceeding the performance of traditional DL frameworks such as LSTM (93.06%), CNN+LSTM (93.31%), and GRU+LSTM (92.20%). Moreover, our model exhibited a noteworthy enhancement in recall for negative sentiments, escalating from 86% (unbalanced dataset) to 96% (balanced dataset), thereby ensuring a more equitable and just sentiment classification. Furthermore, the model diminished misclassification loss from 20.24% for unbalanced to 13.3% for balanced dataset, signifying enhanced generalization and resilience.