Aspect-based Opinion Summarization with Convolutional Neural Networks
This work addresses aspect-based opinion summarization for product reviews, offering more precise aspect extraction compared to general methods, though it is incremental in applying CNNs to this domain.
The paper tackled aspect-based opinion summarization by proposing two CNN-based methods, cascaded and multitask CNNs, for aspect mapping and sentiment classification, achieving significant performance improvements over SVM-based methods with multitask CNN generally performing better.
This paper considers Aspect-based Opinion Summarization (AOS) of reviews on particular products. To enable real applications, an AOS system needs to address two core subtasks, aspect extraction and sentiment classification. Most existing approaches to aspect extraction, which use 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, directly mapping each review sentence into pre-defined aspects. To tackle aspect mapping and sentiment classification, we propose two Convolutional Neural Network (CNN) based methods, cascaded CNN and multitask CNN. Cascaded CNN contains two levels of convolutional networks. Multiple CNNs at level 1 deal with aspect mapping task, and a single CNN at level 2 deals with sentiment classification. Multitask CNN also contains multiple aspect CNNs and a sentiment CNN, but different networks share the same word embeddings. Experimental results indicate that both cascaded and multitask CNNs outperform SVM-based methods by large margins. Multitask CNN generally performs better than cascaded CNN.