Location-aware personalized keyword query recommendation
Yaopei LIANG, Dingming Wu · JOURNAL OF SHENZHEN UNIVERSITY SCIENCE AND ENGINEERING · 2019
The query recommendation provides several alternative queries based on the input query. By using the recommended queries, the users may retrieve more relevant information. Location-aware keyword query recommendation aims for suggesting queries which are able to retrieve the relevant information close to the user's location. When the submitted queries are ambiguous and have various background preferences, the personalized recommendation queries can retrieve information that meets users' preferences. This paper studies a new method of query recommendation, i. e., the location-aware personalized keyword query recommendation. The queries suggested by this approach are able to retrieve nearby relevant information that matches the users' preferences. The proposed method establishes the semantic relationships among keyword queries via a keyword-document bipartite graph. The weights of edges in the keyword-document bipartite graph are dynamically adjusted to represent the spatial proximity of documents. The users' preferences are modeled by the category-based vectors. The random walk with restart model is used to compute recommended queries. This paper develops an efficient algorithm and data structures for the computation of recommendations. The experiments on a real data set AOL demonstrate the effectiveness of the proposed method.