Bring User Interest to Related Entity Recommendation

Most existing approaches to query recommendation focus on query-term or click based analysis over the user session log or click-through data. For entity query, however, finding the relevant queries from these resources is far from trivial. Entity query is a special kind of short queries that commonly appear in image search, video search or object search. Focusing on related entity recommendation, this paper proposes to collect rich related entities of interest from a large number of entity-oriented web pages. During the collection, we maintain a large-scale and general-purpose related entity network (REN), based upon a special co-occurrence relation between the related entity and target entity. Benefiting from the REN, we can easily incorporate various types of related entity into recommendation. Different ranking methods are employed to recommend related and diverse entities of interest. Extensive experiments are conducted to assess the recommendation performance in term of Accuracy and Serendipity. Experimental results show that the REN is a good recommendation resource with high quality of related entities. For recommending related entity, the proposed REN-based method achieves good performance compared with a state-of-the-art relatedness measurement and two famous recommendation systems.

[1]  Olfa Nasraoui,et al.  Mining search engine query logs for query recommendation , 2006, WWW '06.

[2]  Saul Vargas,et al.  Rank and relevance in novelty and diversity metrics for recommender systems , 2011, RecSys '11.

[3]  W. Bruce Croft,et al.  Diversity by proportionality: an election-based approach to search result diversification , 2012, SIGIR '12.

[4]  Qi He,et al.  Web Query Recommendation via Sequential Query Prediction , 2009, 2009 IEEE 25th International Conference on Data Engineering.

[5]  Praveen Paritosh,et al.  Freebase: a collaboratively created graph database for structuring human knowledge , 2008, SIGMOD Conference.

[6]  Alejandro López-Ortiz,et al.  Orthogonal query recommendation , 2013, RecSys.

[7]  Reynold Cheng,et al.  DQR: a probabilistic approach to diversified query recommendation , 2012, CIKM '12.

[8]  Ian H. Witten,et al.  An open-source toolkit for mining Wikipedia , 2013, Artif. Intell..

[9]  Yen-Jen Oyang,et al.  Relevant term suggestion in interactive web search based on contextual information in query session logs , 2003, J. Assoc. Inf. Sci. Technol..

[10]  Haixun Wang,et al.  Probase: a probabilistic taxonomy for text understanding , 2012, SIGMOD Conference.

[11]  Mouzhi Ge,et al.  Beyond accuracy: evaluating recommender systems by coverage and serendipity , 2010, RecSys '10.

[12]  Ricardo A. Baeza-Yates,et al.  Query Recommendation Using Query Logs in Search Engines , 2004, EDBT Workshops.

[13]  Sangkeun Lee,et al.  Random walk based entity ranking on graph for multidimensional recommendation , 2011, RecSys '11.

[14]  Aristides Gionis,et al.  Improving recommendation for long-tail queries via templates , 2011, WWW.

[15]  Enhong Chen,et al.  Context-aware query suggestion by mining click-through and session data , 2008, KDD.

[16]  Ji-Rong Wen,et al.  Clustering user queries of a search engine , 2001, WWW '01.

[17]  Sergey Brin,et al.  The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[18]  Doug Beeferman,et al.  Agglomerative clustering of a search engine query log , 2000, KDD '00.

[19]  Arjen P. de Vries,et al.  Combining implicit and explicit topic representations for result diversification , 2012, SIGIR '12.

[20]  Ravi Kumar,et al.  Automatic Wrappers for Large Scale Web Extraction , 2011, Proc. VLDB Endow..

[21]  Jon Kleinberg,et al.  Authoritative sources in a hyperlinked environment , 1999, SODA '98.

[22]  Aristides Gionis,et al.  The query-flow graph: model and applications , 2008, CIKM '08.

[23]  Thorsten Joachims,et al.  Training linear SVMs in linear time , 2006, KDD '06.

[24]  Wei-Ying Ma,et al.  Object-level Vertical Search , 2007, CIDR.