Aspect Based Sentiment Analysis using Deep Learning Algorithm: A Review

Abstract

Compared to broad sentiment analysis, aspect-based sentiment analysis (ABSA), which aims to predict the sentiment polarities of the designated features or entities in text, can produce more precise results. Product reviews and social media comments are examples of texts that can be used to identify and analyze sentiments. Another type of text analysis is known as sentiment analysis subtask, or ABSA. Deep learning methods have demonstrated efficacy in managing the intricacy of natural language and obtaining subtle emotions linked to many facets of a good or service. Deep learning has become increasingly popular in many applications, and in recent years, both the academic and industry communities have given ABSA a great deal of attention. Overall, ABSA’s deep learning efforts have been successful in advancing sentiment analysis skills, which has given rise to important insights into how consumers view and respond to various features of goods and services. Deep learning-based methods are probably going to have a big impact on how sentiment analysis apps develop in the future as technology keeps developing. The size of the dataset, the task’s difficulty, and the computer resources available all play a role in the deep learning method selection. To attain optimal performance, many state-of-the-art ABSA models pretrain on huge corpora and then fine-tune on task-specific datasets.