Web APIs Recommendation for Mashup Development Based on Hierarchical Dirichlet Process and Factorization Machines

Mashup technology, which allows software developers to compose existing Web APIs to create new or value-added composite RESTful Web services, has emerged as a promising software development method in a service-oriented environment. More and more service providers have published tremendous Web APIs on the internet, which makes it becoming a significant challenge to discover the most suitable Web APIs to construct user-desired Mashup application from these tremendous Web APIs. In this paper, we combine hierarchical dirichlet process and factorization machines to recommend Web APIs for Mashup development. This method, firstly use the hierarchical dirichlet process to derive the latent topics from the description document of Mashups and Web APIs. Then, it apply factorization machines train the topics obtained by the HDP for predicting the probability of Web APIs invocated by Mashups and recommending the high-quality Web APIs for Mashup development. Finally, we conduct a comprehensive evaluation to measure performance of our method. Compared with other existing recommendation approaches, experimental results show that our approach achieves a significant improvement in terms of MAE and RMSE.

[1]  Minglu Li,et al.  A Social-Aware Service Recommendation Approach for Mashup Creation , 2013, ICWS.

[2]  Chao Liu,et al.  Recommender systems with social regularization , 2011, WSDM '11.

[3]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[4]  Cinzia Cappiello,et al.  Quality-Based Recommendations for Mashup Composition , 2010, ICWE Workshops.

[5]  Cinzia Cappiello,et al.  A Quality Model for Mashup Components , 2009, ICWE.

[6]  Wei Tan,et al.  An Empirical Study of Programmable Web: A Network Analysis on a Service-Mashup System , 2012, 2012 IEEE 19th International Conference on Web Services.

[7]  Zibin Zheng,et al.  WSRec: A Collaborative Filtering Based Web Service Recommender System , 2009, 2009 IEEE International Conference on Web Services.

[8]  Wei Zhang,et al.  Service Recommendation for Mashup Composition with Implicit Correlation Regularization , 2015, 2015 IEEE International Conference on Web Services.

[9]  Liang Chen,et al.  Manifold-Learning Based API Recommendation for Mashup Creation , 2015, 2015 IEEE International Conference on Web Services.

[10]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[11]  Zibin Zheng,et al.  WT-LDA: User Tagging Augmented LDA for Web Service Clustering , 2013, ICSOC.

[12]  Cesare Pautasso,et al.  Information Quality in Mashups , 2010, IEEE Internet Computing.

[13]  Zibin Zheng,et al.  Web Service Recommendation via Exploiting Location and QoS Information , 2014, IEEE Transactions on Parallel and Distributed Systems.

[14]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[15]  Zibin Zheng,et al.  Collaborative Web Service QoS Prediction via Neighborhood Integrated Matrix Factorization , 2013, IEEE Transactions on Services Computing.

[16]  Xumin Liu,et al.  Incorporating User, Topic, and Service Related Latent Factors into Web Service Recommendation , 2015, 2015 IEEE International Conference on Web Services.

[17]  Cheng Wu,et al.  Category-Aware API Clustering and Distributed Recommendation for Automatic Mashup Creation , 2015, IEEE Transactions on Services Computing.

[18]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[19]  Yee Whye Teh,et al.  Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes , 2004, NIPS.

[20]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[21]  Hiroshi Nakagawa,et al.  The Hybrid Nested/Hierarchical Dirichlet Process and its Application to Topic Modeling with Word Differentiation , 2015, AAAI.