Aspect-Based Sentiment Quantification

In the current literature, many methods have been devised for sentiment quantification. In this work, we propose AspEntQuaNet, one of the first methods for aspect-based sentiment quantification. It extends the state-of-the-art QuaNet deep learning method for sentiment quantification in two ways. First, it considers aspects and ternary sentiment quantification concerning these aspects instead of binary sentiment quantification. Second, it improves on the results of QuaNet with an entropy-based sorting procedure instead of multisorting. Other sentiment quantification methods have also been adapted for ternary sentiment quantification instead of binary sentiment quantification. Using the modified version of the SemEval 2016 dataset for aspect-based sentiment quantification, we show that AspEntQuaNet is superior to all other considered existing methods based on obtained results for various aspect categories. In particular, AspEntQuaNet outperforms QuaNet often by a factor of 2 on all considered evaluation measures.

Automated summary

This paper proposes a method called AspEntQuaNet for aspect-based sentiment quantification, which extends the QuaNet deep learning method and improves it by considering aspects, ternary sentiment quantification, and using an entropy-based sorting procedure. The results show that AspEntQuaNet outperforms other existing methods on the SemEval 2016 dataset.