Abstract
With the development of cloud computing technologies, eBusiness systems and applications pay more attention on customer reviews, such as commodity, customer's emotion. These review data contain a vast amount of valuable information. It is challenging to extract knowledge from these reviews in cloud environment, because they are massive, usually distributed, and keep constantly changing. In this paper, a novel framework to extract knowledge from Chinese review data is proposed, which mainly includes building knowledge space, retrieving knowledge and optimizing results. For Chinese reviews, a skip-gram-based model is used to train review data and generate the knowledge space. To quickly build knowledge space, an algorithm based on hierarchical softmax is proposed, which does not need any feature extraction and modelization. This algorithm is applicable for massive data and conveniently extended in cloud environment. When retrieving knowledge and optimizing results, our framework uses euclidean distance to find the knowledge, closely linked to the query, and uses 2-gram algorithm to optimize the results. Experimental results show that our framework is practical and efficient.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.