Cascaded Convolutional Neural Networks for Aspect-Based Opinion Summary

Abstract

This paper studies aspect-based opinion summary (AOS) of reviews on particular products. In practice, an AOS system needs to address two core subtasks, aspect extraction and sentiment classification. Most existing approaches to aspect extraction, using linguistic analysis or topic modeling, are general across different products but not precise enough or suitable for particular products. Instead we take a less general but more precise scheme, which directly maps each review sentence into pre-defined aspects. To tackle aspect mapping and sentiment classification, we propose a convolutional neural network (CNN) based method, cascaded CNN (C-CNN). C-CNN contains two levels of convolutional networks. Multiple CNNs at level 1 deal with aspect mapping task. If a review sentence belongs to pre-defined aspect categories, a single CNN at level 2 determines its sentiment polarity. Experimental results show that C-CNN with pre-trained word embedding outperform cascaded SVM with feature engineering. We also build a system called OpiSum with C-CNN. The demo of OpiSum can be found at http://114.215.167.42.