A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
This addresses sentiment analysis for domains like reviews by reducing reliance on expensive annotations, though it is incremental as it builds on existing weakly supervised techniques.
The paper tackles weakly supervised document-level multi-aspect sentiment classification by using target-opinion word pairs as supervision, achieving performance comparable to state-of-the-art supervised methods with hundreds of labels per aspect on TripAdvisor and BeerAdvocate datasets.
In this paper, we propose a variational approach to weakly supervised document-level multi-aspect sentiment classification. Instead of using user-generated ratings or annotations provided by domain experts, we use target-opinion word pairs as "supervision." These word pairs can be extracted by using dependency parsers and simple rules. Our objective is to predict an opinion word given a target word while our ultimate goal is to learn a sentiment polarity classifier to predict the sentiment polarity of each aspect given a document. By introducing a latent variable, i.e., the sentiment polarity, to the objective function, we can inject the sentiment polarity classifier to the objective via the variational lower bound. We can learn a sentiment polarity classifier by optimizing the lower bound. We show that our method can outperform weakly supervised baselines on TripAdvisor and BeerAdvocate datasets and can be comparable to the state-of-the-art supervised method with hundreds of labels per aspect.