Aspect extraction is a task to abstract the common properties of objects from cor pora discussing them, such as reviews of products. Recent work on aspect extrac tion is leveraging the hierarchical rela tionship between products and their cate gories. However, such effort focuses on the aspects of child categories but ignores those from parent categories. Hence, we propose an LDA-based generative topic model inducing the two-layer categorical information (CAT-LDA), to balance the aspects of both a parent category and its child categories. Our hypothesis is that child categories inherit aspects from par ent categories, controlled by the hierarchy between them. Experimental results on 5 categories of Amazon.com products show that both common aspects of parent cat egory and the individual aspects of sub categories can be extracted to align well with the common sense. We further eval uate the manually extracted aspects of 16 products, resulting in an average hit rate of 79.10%.
展开▼
