Stars Are All You Need: A Distantly Supervised Pyramid Network for Unified Sentiment Analysis

Data for the Rating Prediction (RP) sentiment analysis task such as star reviews are readily available. However, data for aspect-category detection (ACD) and aspect-category sentiment analysis (ACSA) is often desired because of the fine-grained nature but are expensive to collect. In this work, we propose Unified Sentiment Analysis (Uni-SA) to understand aspect and review sentiment in a unified manner. Specifically, we propose a Distantly Supervised Pyramid Network (DSPN) to efficiently perform ACD, ACSA, and RP using only RP labels for training. We evaluate DSPN on multi-aspect review datasets in English and Chinese and find that in addition to the internal efficiency of sample size, DSPN also performs comparably well to a variety of benchmark models. We also demonstrate the interpretability of DSPN's outputs on reviews to show the pyramid structure inherent in unified sentiment analysis.