AWSR: Active Web Service Recommendation Based on Usage History

Web services are very prevalent nowadays. Recommending Web services that users are interested in becomes an interesting and challenging research problem. In this paper, we present AWSR (Active Web Service Recommendation), an effective Web service recommendation system based on users' usage history to actively recommend Web services to users. AWSR extracts user's functional interests and QoS preferences from his/her usage history. Similarity between user's functional interests and a candidate Web service is calculated first. A hybrid new metric of similarity is developed to combine functional similarity measurement and nonfunctional similarity measurement based on comprehensive QoS of Web services. The AWSR ranks publicly available Web services based on values of the hybrid metric of similarity, so that a Top-K Web service recommendation list is created for a user. AWSR has been implemented and deployed on the Web. By conducting large-scale experiments based on a real-world Web services dataset, it is shown that our system effectively recommends Web services based on users functional interests and non-functional requirements with excellent performance.

[1]  Junfeng Zhao,et al.  Personalized QoS Prediction forWeb Services via Collaborative Filtering , 2007, IEEE International Conference on Web Services (ICWS 2007).

[2]  Xi Chen,et al.  RegionKNN: A Scalable Hybrid Collaborative Filtering Algorithm for Personalized Web Service Recommendation , 2010, 2010 IEEE International Conference on Web Services.

[3]  Stephen E. Robertson,et al.  Understanding inverse document frequency: on theoretical arguments for IDF , 2004, J. Documentation.

[4]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[5]  Qiong Zhang,et al.  Collaborative Filtering Based Service Ranking Using Invocation Histories , 2011, 2011 IEEE International Conference on Web Services.

[6]  Maude Manouvrier,et al.  QoS-Driven Selection of Web Services for Transactional Composition , 2008, 2008 IEEE International Conference on Web Services.

[7]  Zibin Zheng,et al.  QoS-Aware Web Service Recommendation by Collaborative Filtering , 2011, IEEE Transactions on Services Computing.

[8]  A. M. Madni,et al.  Recommender systems in e-commerce , 2014, 2014 World Automation Congress (WAC).

[9]  Karen Spärck Jones.  A statistical interpretation of term specificity and its application in retrieval , 2021, J. Documentation.

[10]  Zibin Zheng,et al.  WSExpress: A QoS-aware Search Engine for Web Services , 2010, 2010 IEEE International Conference on Web Services.

[11]  Jinjun Chen,et al.  Combining Local Optimization and Enumeration for QoS-aware Web Service Composition , 2010, 2010 IEEE International Conference on Web Services.

[12]  Mingdong Tang,et al.  Web Service Selection for Resolving Conflicting Service Requests , 2011, 2011 IEEE International Conference on Web Services.

[13]  Mingdong Tang,et al.  An Effective Web Service Recommendation Method Based on Personalized Collaborative Filtering , 2011, 2011 IEEE International Conference on Web Services.

[14]  Sophie Ahrens,et al.  Recommender Systems , 2012 .

[15]  Jaana Kekäläinen,et al.  Cumulated gain-based evaluation of IR techniques , 2002, TOIS.

[16]  Thomas Risse,et al.  Selecting skyline services for QoS-based web service composition , 2010, WWW '10.

[17]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[18]  John Riedl,et al.  Explaining collaborative filtering recommendations , 2000, CSCW '00.

[19]  Thomas Risse,et al.  Combining global optimization with local selection for efficient QoS-aware service composition , 2009, WWW '09.

[20]  Vincenzo Grassi,et al.  Flow-Based Service Selection forWeb Service Composition Supporting Multiple QoS Classes , 2007, IEEE International Conference on Web Services (ICWS 2007).