Modeling Temporal Effectiveness for Context-Aware Web Services Recommendation

Context-Aware Recommender System (CARS) aims to not only recommend services similar to those already rated with the highest score, but also provide opportunities for exploring the important role of temporal, spatial and social contexts for personalized web services recommendation. A key step for temporal-based CARS methods is to explore the time decay process of past invocation records to make the Quality of Services (QoS) prediction. However, it is a nontrivial task to model the temporal effects on web services recommendation, due to the dynamic features of contextual information in view of temporal spatial correlations. For instance, in location-aware services recommendation, the user's geographical position would change very frequently as time goes on. In this paper, we propose a Context-Aware Services Recommendation based on Temporal Effectiveness (CASR-TE) method. Inspired by existing time decay approaches, we first present an enhanced temporal decay model combining the time decay function with traditional similarity measurement methods. Then, we model temporal spatial correlations as well as their impacts on the user preference expansion. Finally, we evaluate the CASR-TE method on WS-Dream dataset by evaluation matrices of both RMSE and MAE. Experimental results show that our approach outperforms several benchmark methods with a significant margin.

[1]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[2]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.

[3]  David Heckerman,et al.  Empirical Analysis of Predictive Algorithms for Collaborative Filtering , 1998, UAI.

[4]  Bo Hu,et al.  Spatio-Temporal Topic Modeling in Mobile Social Media for Location Recommendation , 2013, 2013 IEEE 13th International Conference on Data Mining.

[5]  Mingdong Tang,et al.  Location-Aware Collaborative Filtering for QoS-Based Service Recommendation , 2012, 2012 IEEE 19th International Conference on Web Services.

[6]  Zibin Zheng,et al.  Mashup Service Recommendation Based on User Interest and Social Network , 2013, 2013 IEEE 20th International Conference on Web Services.

[7]  Jia Zhang,et al.  Time-Aware Service Recommendation for Mashup Creation in an Evolving Service Ecosystem , 2014, 2014 IEEE International Conference on Web Services.

[8]  Chong Wang,et al.  Web Service Recommendation Based on Watchlist via Temporal and Tag Preference Fusion , 2014, 2014 IEEE International Conference on Web Services.

[9]  Hailong Sun,et al.  Incorporating Invocation Time in Predicting Web Service QoS via Triadic Factorization , 2014, 2014 IEEE International Conference on Web Services.

[10]  Huan Liu,et al.  Modeling temporal effects of human mobile behavior on location-based social networks , 2013, CIKM.

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

[12]  John McCarthy,et al.  Notes on Formalizing Context , 1993, IJCAI.

[13]  Francesco Ricci,et al.  Context-Aware Recommender Systems , 2011, AI Mag..

[14]  Xiaohui Hu,et al.  A Time-Aware and Data Sparsity Tolerant Approach for Web Service Recommendation , 2014, 2014 IEEE International Conference on Web Services.

[15]  Ruisheng Zhang,et al.  Context-Aware Web Services Recommendation Based on User Preference , 2014, 2014 Asia-Pacific Services Computing Conference.

[16]  Patrick Brézillon.  Task-Realization Models in Contextual Graphs , 2005, CONTEXT.

[17]  Zibin Zheng,et al.  Location-Based Hierarchical Matrix Factorization for Web Service Recommendation , 2014, 2014 IEEE International Conference on Web Services.

[18]  Yuxin Mao,et al.  Personalized Services Recommendation Based on Context-Aware QoS Prediction , 2012, 2012 IEEE 19th International Conference on Web Services.

[19]  Paul Dourish,et al.  What we talk about when we talk about context , 2004, Personal and Ubiquitous Computing.