Research and Application of Text-Based Sentiment Analytics

Abstract

Text-based sentiment analytics is an important research direction in the field of natural language processing, and it is widely applied in identifying emotional tendencies. The proliferation of e-commerce platforms has underscored the criticality of emotional tendencies and user experiences delineated in product reviews for gauging product quality and user satisfaction. This study presents a developed text-based sentiment analysis system tailored to product reviews on ecommerce platforms. Three distinct text-based sentiment classification models based on Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Bidirectional Encoder Representations from Transformers (BERT) were constructed and implemented. Subsequently, sentiment classification and comparative experiments were conducted utilizing real-world product review data. The experimental outcomes underscore that the BERT model outperforms others in terms of the Area Under the Curve (AUC) metric, yielding superior results in the domain of text sentiment analysis. This paper extensively deliberates on the fusion of deep learning methodologies into sentiment analytics, encapsulating the entire spectrum of data collection, preprocessing, and model analysis, with an overarching goal of providing a reference point for research endeavors in analogous realms.