Using Relational Topic Model and Factorization Machines to Recommend Web APIs for Mashup Creation

The rapid growth in the number of Web APIs, coupled with the myriad of functionally similar Web APIs, makes it difficult to find suitable Web APIs to develop Mashup applications. Even if the existing Web APIs recommendation methods show improvements in service discovery, the accuracy of them can be significantly improved due to overlooking the impact of sparsity and dimension of relationships between Mashup and Web APIs on recommendation accuracy. In this paper, we propose a Web APIs recommendation method for Mashup creation by combining relational topic model and factorization machines technique. This method firstly uses relational topic model to characterize the relationships among Mashup, Web APIs, and their links, and mine the latent topics derived by the relationships. Secondly, it exploits factorization machines to train the latent topics for predicting the link relationship among Mashup and Web APIs to recommend adequate relevant top-k Web APIs for target Mashup creation. 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 precision, recall, and F-measure.

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

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

[3]  Freddy Lécué,et al.  Semantic content-based recommendation of software services using context , 2013, TWEB.

[4]  Jinpeng Huai,et al.  A Probabilistic Approach for Web Service Discovery , 2013, 2013 IEEE International Conference on Services Computing.

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

[6]  David M. Blei,et al.  Relational Topic Models for Document Networks , 2009, AISTATS.

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

[8]  Arun Iyengar,et al.  Combining Quality of Service and Social Information for Ranking Services , 2009, ICSOC/ServiceWave.

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

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

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

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

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

[14]  Hailong Sun,et al.  A Novel Approach for API Recommendation in Mashup Development , 2014, 2014 IEEE International Conference on Web Services.

[15]  Lina Yao,et al.  Unified Collaborative and Content-Based Web Service Recommendation , 2015, IEEE Transactions on Services Computing.

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

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

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

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

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