Hits:

Indexed by:会议论文

Date of Publication:2016-10-29

Included Journals:EI、CPCI-S

Volume:669

Page Number:186-193

Key Words:Text summarization; Topic models; User-oriented summarization

Abstract:Text summarization techniques are widely used to generate abstracts of documents automatically, facilitating users to capture the needed information from a large amount of documents. However, it poses a great challenge to satisfy the information needs of users in different roles while keeping the most important information. To solve this problem, we propose a novel framework on text summarization, which incorporates historical information of users to generate a user-oriented personalized summarization. The framework adopts two topic models to model the comments of doctors and patients from health-related social networks about certain diseases, and then identifies topics that the two kinds of users are interested in. Based on the identified topics, we propose three methods for sentence ranking to generate summarizations about the diseases for doctors and patients, respectively. Experimental results show a high similarity between the generated summarization and the real interests of different users, better meeting the information needs while keeping the summarization performance.