Journal
NEW REVIEW OF HYPERMEDIA AND MULTIMEDIA
Volume 19, Issue 1, Pages 3-24Publisher
TAYLOR & FRANCIS LTD
DOI: 10.1080/13614568.2013.766266
Keywords
Chinese product reviews; Feature-opinion pair (FOP); Domain ontology; Opinion mining; Design science; Social commerce
Categories
Ask authors/readers for more resources
With the emergence of the new economy based on social media, a great amount of consumer feedback on particular products are conveyed through wide-spreading product online reviews, making opinion mining a growing interest for both academia and industry. According to the characteristic mode of expression in Chinese, this research proposes an ontology-based linguistic model to identify the basic appraisal expression in Chinese product reviewsfeature-opinion pair (FOP). The product-oriented domain ontology is constructed automatically at first, then algorithms to identify FOP are designed by mapping product features and opinions to the conceptual space of the domain ontology, and finally comparative experiments are conducted to evaluate the model. Experimental results indicate that the performance of the proposed approach in this paper is efficient in obtaining a more accurate result compared to the state-of-art algorithms. Furthermore, through identifying and analyzing FOPs, the unstructured product reviews are converted into structured and machine-sensible expression, which provides valuable information for business application. This paper contributes to the related research in opinion mining by developing a solid foundation for further sentiment analysis at a fine-grained level and proposing a general way for automatic ontology construction.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available