Leveraging Deep Learning Models for Automated Aspect Based Sentiment Analysis and Classification

Abstract

Aspect-based Sentiment Analysis (ABSA) is a subdomain of Sentiment Analysis (SA) that focuses on detecting the sentiment toward features of a product or particular aspects, experience, or service. ABSA targets to go beyond simple sentiment classification of a sentence or document and present a more granular study of sentiment towards different aspects. ABSA has several real-time applications, which include social media monitoring, customer feedback analysis, and product reviews. Many difficulties exist in ABSA, including dealing with language variability and complexity, sentiment subjectivity, and managing multiple aspects in a single sentence. Recently, Deep Learning (DL) methods continued to be an active area of research and proved a promising model in ABSA. This study focuses on designing and developing ABSA models using DL concepts. The presented ABSA model aims to identify the sentiments in the direction of particular aspects or features of a product, service, or experience. The presented approach initially accomplishes diverse phases of data pre-processing to convert the input data meaningfully. In addition, the word2vec model is applied as a feature extraction approach. For sentiment analysis, three DL models are employed, namely Hopfield Network (HN), Convolutional Neural Network (CNN), and Bidirectional Long Short Term Memory (BiLSTM) approaches. The experimental validation of the DL models occurs utilizing a benchmark dataset. The simulation values highlighted that the CNN model exhibits improved sentiment classification results over other DL models.