Stars Are All You Need: A Distantly Supervised Pyramid Network for Document-Level End-to-End Sentiment Analysis
Preprint
Abstract
In this paper, we propose document-level end-to-end sentiment analysis to efficiently understand aspect and review sentiment expressed in online reviews in a unified manner. In particular, we assume that star rating labels are a "coarse-grained synthesis" of aspect ratings across in the review. We propose a Distantly Supervised Pyramid Network (DSPN) to efficiently perform Aspect-Category Detection, Aspect-Category Sentiment Analysis, and Rating Prediction using only document star rating labels for training. By performing these three related sentiment subtasks in an end-to-end manner, DSPN can extract aspects mentioned in the review, identify the corresponding sentiments, and predict the star rating labels. We evaluate DSPN on multi-aspect review datasets in English and Chinese and find that with only star rating labels for supervision, DSPN can perform 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 document level end-to-end sentiment analysis.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis2022
- Understanding and Predicting Users’ Rating Behavior: A Cognitive PerspectiveINFORMS Journal on Computing, 2020
- Uniting the Tribes: Using Text for Marketing InsightJournal of Marketing, 2019
- W2VLDA: Almost unsupervised system for Aspect Based Sentiment AnalysisExpert Systems with Applications, 2018
- INSIGHT-1 at SemEval-2016 Task 5: Deep Learning for Multilingual Aspect-based Sentiment Analysis2016
- Survey on Aspect-Level Sentiment AnalysisIEEE Transactions on Knowledge and Data Engineering, 2015