cc 17(12): e4

Research Article

An Augmented User Model for Personalized Search in Collaborative Social Tagging Systems

Download114 downloads
  • @ARTICLE{10.4108/eai.9-10-2017.154549,
        author={Wenyu Zhao and Dong Zhou and Xuan Wu and S\^{e}amus Lawless and Jianxun Liu},
        title={An Augmented User Model for Personalized Search in Collaborative Social Tagging Systems},
        journal={EAI Endorsed Transactions on Collaborative Computing},
        volume={3},
        number={12},
        publisher={EAI},
        journal_a={CC},
        year={2017},
        month={10},
        keywords={Personalized Social Search, Collaborative Social Tagging Systems, Latent Dirichlet Allocation, Neural Language Model, Query Expansion},
        doi={10.4108/eai.9-10-2017.154549}
    }
    
  • Wenyu Zhao
    Dong Zhou
    Xuan Wu
    Séamus Lawless
    Jianxun Liu
    Year: 2017
    An Augmented User Model for Personalized Search in Collaborative Social Tagging Systems
    CC
    EAI
    DOI: 10.4108/eai.9-10-2017.154549
Wenyu Zhao1, Dong Zhou1,*, Xuan Wu1, Séamus Lawless2, Jianxun Liu1
  • 1: School of Computer Science and Engineering & Key Laboratory of Knowledge Processing and Networked Manufacturing, Hunan University of Science and Technology, Xiangtan, Hunan 411201, China
  • 2: ADAPT Centre, Knowledge and Date Engineering Group, School of Computer Science and Statistics, Trinity College Dublin, Dublin 2, Ireland
*Contact email: dongzhou1979@hotmail.com

Abstract

Alongside the enormous volume of user-generated content posted to World Wide Web, there exists a thriving demand for search personalization services. To provide personalized services, a user model is usually required. We address the setting adopted by the majority of previous work, where a user model consists solely of the user’s past information. We construct an augmented user model from a number of tags and documents. These resources are further processed according to the user’s past information by exploring external knowledge base. A novel generative model is proposed for user model generation. This model utilizes recent advances in neural language models such as Word Embeddings with latent semantic models such as Latent Dirichlet Allocation. We further present a new query expansion method to facilitate the desired personalized retrieval. Experiments conducted on two real-world collaborative social tagging datasets show that our proposed methods outperform state-of-the-art methods.