White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

User Information Modelling in Social Communities and Networks

Yang, Baoguo (2015) User Information Modelling in Social Communities and Networks. PhD thesis, University of York.

Thesis_Yang.pdf - Examined Thesis (PDF)
Available under License Creative Commons Attribution-Noncommercial-No Derivative Works 2.0 UK: England & Wales.

Download (3152Kb) | Preview


User modelling is the basis for social network analysis, such as community detection, expert finding, etc. The aim of this research is to model user information including user-generated content and social ties. There have been many algorithms for community detection. However, the existing algorithms consider little about the rich hidden knowledge within communities of social networks. In this research, we propose to simultaneously discover communities and the hidden/latent knowledge within them. We focus on jointly modelling communities, user sentiment topics, and the social links. We also learn to recommend experts to the askers based on the newly posted questions in online question answering communities. Specifically, we first propose a new probabilistic model to depict users' expertise based on answers and their descriptive ability based on questions. To exploit social information in community question answering (CQA), the link analysis is also considered. We also propose a user expertise model under tags rather than the general topics. In CQA sites, it is very common that some users share the same user names. Once an ambiguous user name is recommended, it is difficult for the asker to find out the target user directly from the large scale CQA site. We propose a simple but effective method to disambiguate user names by ranking their tag-based relevance to a query question. We evaluate the proposed models and methods on real world datasets. For community discovery, our models can not only identify communities with different topic-sentiment distributions, but also achieve comparable performance. With respect to the expert recommendation in CQA, the unified modelling of user topics/tags and abilities are capable of improving the recommendation performance. Moreover, as for the user name disambiguation in CQA, the proposed method can help question askers match the ambiguous user names with the right people with high accuracy.

Item Type: Thesis (PhD)
Academic Units: The University of York > Computer Science (York)
Identification Number/EthosID: uk.bl.ethos.727322
Depositing User: Baoguo Yang
Date Deposited: 22 Nov 2017 14:05
Last Modified: 24 Jul 2018 15:23
URI: http://etheses.whiterose.ac.uk/id/eprint/18567

You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.

Actions (repository staff only: login required)