Learning Polarity Embedding Attention for Aspect-based Sentiment Analysis

The primary goal of Sentiment Analysis (SA) is to recognize the emotions present in natural language text. Generally, in opinion content, emotions are often driven by several aspects of their interests. Any SA task that groups data into various aspects and identifies sentiments is referred to as Aspect-Based Sentiment Analysis (ABSA). Recent advances in Deep Learning (DL) have brought revolutionary changes in the performance of Machine Learning models. Their ability to capture semantic and syntactic traits of any intrinsic data model is highly appreciated. In this research work, we use DL techniques to address the challenges of ABSA aiming to improve sentiment granularity at the aspect level. The proposed methodology works in two stages: (i) aspect terms extraction and (ii) sentiment polarity classification. The task of aspect terms extraction is achieved through the concept of Named-Entity Recognition (NER). However, most of the available NER models are domain dependent and utilize hand-crafted features for learning labeled data. Hence, for aspect terms extraction, a joint model based on Bi-GRU and Conditional Random Fields (CRF) is proposed. Similarly, for sentiment polarity classification, we introduce a novel attention-based neural network called Polarity Embedded Attention Network (PEAN). The intuition behind the PEAN is that, when an aspect term appears in a sentence, its related sentiment term is represented by the polarity embedding. Hence, PEAN combines sentence embedding with aspect and polarity embedding to learn the relationship between sentence and aspect terms. The effectiveness of the proposed model is realized through a comparative study of different models on benchmark datasets. It yields better results compared to other baseline techniques.