BJUT at TREC 2014 Contextual Suggestion Track: Hybrid Recommendation Based on Open-web Information
Hanchen Li, Zhen Chao Yang, Yingxu Lai, Lijuan Duan, Kefeng Fan · 2014
In this paper we describe our efforts for TREC contex-tual suggestion task. Our goal of this year is to evalu-ate the effectiveness of: (1) Preference crawling method that as far as possible to obtain more candidate spots’ information from open-web to model the users ’ inter-est profiles; (2) Automatic summarization method that leverages the information from multiple resources to generate the description for each candidate scenic spot-s; (3) Hybrid recommendation method that combing a variety of factors to construct a system of hybrid rec-ommendation system. Finally, we conduct extensive ex-periments to evaluate the proposed framework on TREC 2014 Contextual Suggestion data set, and, as would be expected, the results demonstrate its generality and su-perior performance.