A Hybrid Approach to Service Recommendation Based on Network Representation Learning
Authors:
Open Access
- 1 May 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 60242-60254
Abstract
Network representation learning has attracted much attention as a new learning paradigm to embed network vertices into a low-dimensional vector space, by preserving network information. In this paper, in the light of user co-tag network and social network, we introduced network representation learning techniques into the learning of user preference, to encode user social relations into a continuous vector space. Firstly, we proposed a hybrid network representation learning approach to effectively utilize users’ tagging and social relationships, and then we took it for service recommendation. The experiment results show that the improvements of performance, compared with three baselines on two public data sets, the improvement ratio over the baselines is up to 50% in terms of Recall@10 and Precision@10, and the improvement is even more than 90% in terms of NDGG@10 and MRR@10.Keywords
Funding Information
- National Key Research and Development Program of China (2017YFB1400602)
- National Natural Science Foundation of China (61572371, 61702377)
- Science and Technology Innovation Program of Hubei Province (2018ACA133)
- Educational Commission of Hubei Province (Q20171008)
This publication has 26 references indexed in Scilit:
- Topic model-based recommendation system for media re-creation service2016
- Personalized Service Recommendation for Collaborative Tagging Systems with Social Relations and Temporal Influences2016
- Structural Deep Network Embedding2016
- node2vec2016
- LINE2015
- Interpreting the Public Sentiment Variations on TwitterIEEE Transactions on Knowledge and Data Engineering, 2013
- Mashup Service Recommendation Based on User Interest and Social Network2013
- A method of personalized recommendation based on multi-label propagation for overlapping community detection2012
- Improving recommendation quality by merging collaborative filtering and social relationships2011
- Improving the accuracy and efficiency of tag recommendation system by applying hybrid methods2011