Use this URL to cite or link to this record in EThOS:
Title: Modelling viewpoints in user generated content
Author: Despotakis, Dimoklis
Awarding Body: University of Leeds
Current Institution: University of Leeds
Date of Award: 2013
Availability of Full Text:
Access from EThOS:
Access from Institution:
The Web 2.0 infrastructure allowed for a tremendous technological growth in the ways that information is distributed and exchanged among individuals. Web sites transformed to hosts of an abundance of user generated content in various domains comprising thereafter social media platforms. This evolution heralded the beginning of a new era for user modelling. Several types of applications have gained benefit from harvesting social media content for either populating or enriching user models by identifying, extracting and analysing digital user traces aiming at improving system responses for adaptation and personalisation. However, different user experiences and backgrounds determine different user viewpoints, and it is evident that the next generation of user modelling approaches should cater for viewpoints diversity. This can enable better understanding of the users' conceptualisations, their exposure to diverse interpretations overcoming thus the 'filter bubble' effect and enriching their perspective. How can we represent user viewpoints? How can we capture user-viewpoints from user generated content? How can we enable intelligent analysis of user viewpoints to explore diversity? This research complements notable efforts for viewpoints modelling by addressing three main challenges: (i) enable better understanding of users by capturing the semantics of user viewpoints; (ii) formally represent user viewpoints by capturing the viewpoint focus, and identify the projection of user models on the domain of interest; and, (iii) enable exploration of diversity by providing intelligent methods for analysis and comparison of viewpoints. The proposed approach is wrapped within a framework for representing, capturing and analysing user viewpoint semantics, called ViewS. ViewS defines a semantic augmentation pipeline for processing textual user generated content. The semantic output is then used as input together with the annotating ontologies in a component for capturing viewpoint focus which exploits Formal Concept Analysis. The viewpoint focus model is used then to analyse and compare user viewpoints and explore diversity. ViewS has been deployed and evaluated for user viewpoints on social signals in interpersonal communication, including emotion and body language, where diverse interpretations can be obtained by different individuals and groups.
Supervisor: Dimitrova, Vania ; Lau, Lydia ; Thakker, Dhaval Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available