Paper Contents
Abstract
Sentiment analysis, a vital task in natural language processing (NLP), aims to identify and categorize sentiments expressed in textual data. This research utilizes deep learning techniques, fueled by Big Data, to improve the accuracy of sentiment analysis. By training a simple feedforward neural network on a substantial Amazon review dataset, we classify sentiments as positive or negative. The model employs embedding layers to represent words as dense vectors, followed by a global average pooling layer to capture semantic information. A final dense layer with a sigmoid activation function predicts the sentiment probability. The results highlight the effectiveness of deep learning in capturing complex linguistic nuances, achieving an impressive accuracy of 88.47%. This outperforms traditional methods, demonstrating the potential of Big Data and deep learning in sentiment analysis. Future research directions include exploring more advanced architectures, addressing class imbalance issues, improving model interpretability, and incorporating domain-specific knowledge to further elevate sentiment analysis performance.
Copyright
Copyright © 2024 Rakshit Dabral. This is an open access article distributed under the Creative Commons Attribution License.
