scispace - formally typeset
Search or ask a question
Topic

User modeling

About: User modeling is a research topic. Over the lifetime, 10701 publications have been published within this topic receiving 278012 citations.


Papers
More filters
Proceedings ArticleDOI
05 Sep 2012
TL;DR: This paper describes the methodology for the automatic creation and aggregation of interoperable and multi-domain user profiles of interests using semantic technologies, and proposes a user study on different user profiling techniques for social networking websites in general, and for Twitter and Facebook in particular.
Abstract: User profiling techniques have mostly focused on retrieving and representing a user's knowledge, context and interests in order to provide recommendations, personalise search, and build user-adaptive systems. However, building a user profile on a single social network limits the quality and completeness of the profile, especially when interoperability of the profile is key and its reuse on different sites is necessary for providing other types of personalisation. Indeed recent studies have shown that users on the Social Web often use different social networking sites for diverse, and sometimes non-overlapping, purposes and interests. In this paper, we describe our methodology for the automatic creation and aggregation of interoperable and multi-domain user profiles of interests using semantic technologies. Moreover, we propose a user study on different user profiling techniques for social networking websites in general, and for Twitter and Facebook in particular. In this regard, based on the results of our user evaluation, we investigate (i) the accuracy of different methodologies for profiling, (ii) the effect of time decay functions on ranking user interests, and (iii) the benefits of merging different user models using semantic technologies.

81 citations

Proceedings ArticleDOI
19 Jun 2008
TL;DR: This paper compares user tag-clouds from multiple folksonomies to show how they tend to overlap, regardless of the focus of the folksonomy, and demonstrates how this comparison helps finding and aligning the user's separate identities, and shows that cross-linking distributed user tags enriches users profiles.
Abstract: As the popularity of the web increases, particularly the use of social networking sites and style sharing platforms, users are becoming increasingly connected, sharing more and more information, resources, and opinions. This vast array of information presents unique opportunities to harvest knowledge about user activities and interests through the exploitation of large-scale, complex systems. Communal tagging sites, and their respective folksonomies, are one example of such a complex system, providing huge amounts of information about users, spanning multiple domains of interest. However, the current Web infrastructure provides no mechanism for users to consolidate and exploit this information since it is spread over many desperate and unconnected resources. In this paper we compare user tag-clouds from multiple folksonomies to: (a) show how they tend to overlap, regardless of the focus of the folksonomy (b) demonstrate how this comparison helps finding and aligning the user's separate identities, and (c) show that cross-linking distributed user tag-clouds enriches users profiles. During this process, we find that significant user interests are often reflected in multiple Web2.0 profiles, even though they may operate over different domains. However, due to the free-form nature of tagging, some correlations are lost, a problem we address through the implementation and evaluation of a user tag filtering architecture.

80 citations

Patent
05 Jan 2006
TL;DR: In this article, the change in context of a user is propagated to other users in the social network in conjunction with TV content, such as users in a social network's social network.
Abstract: The systems and methods of the present invention provide for a number of improvements to the TV consumption process, including personalization, community viewing, shared presence and context, messaging, access to ratings and recommendations (including community reviews), alerts, etc. One method that the present invention provides allows for the indication of a given user's context to be provided to other users, such as users in the given user's social network. The method comprises generating an indication of a change in context for a given user, the context comprising information regarding an action of the given user. The indication of the change in context for the given user is propagated to one or more users in the social network for the given user. The indication of the change in context of the given user is presented to users in the given user's social network in conjunction with TV content.

80 citations

Book ChapterDOI
02 Oct 2005
TL;DR: This paper introduces a conceptual framework for capturing tool architectures, and then discusses the choices available to designers of tools using this framework, and compares and contrast the main canonical architectures in use today.
Abstract: As model-driven development techniques grow in importance so do the capabilities and features of the tools that support them, especially tools that allow users to customize their modeling language. Superficially, many modeling tools seem to offer similar functionality, but under the surface there are important differences that can have an impact on tool builders and users depending on the tool architecture chosen. At present, however, there is no established conceptual framework for characterizing and comparing different tool architectures. In this paper we address this problem by first introducing a conceptual framework for capturing tool architectures, and then — using this framework — discuss the choices available to designers of tools. We then compare and contrast the main canonical architectures in use today.

80 citations

Book ChapterDOI
13 Jul 2001
TL;DR: The user modelling that takes place in each part of I-Help is described, in particular to effect this matchmaking for Private Discussions, which takes advantage of a distributed multi-agent architecture.
Abstract: This paper describes user modelling in I-Help, a system to facilitate communication amongst learners. There are two I-Help components: Private and Public Discussions. In the Private Discussions learners take part in a one-on-one interaction with a partner (possibly a peer). The Public Discussions are open - everyone in the group has access to all discussion forums relevant to that group. The Public Discussions are most suited to discussion of issues where there might be a variety of valid viewpoints, or different solutions to a problem. It is also useful for straightforward questions and answers that have wide-spread applicability. The Private Discussions are better suited for more intensive interactions involving peer tutoring or in-depth discussions. Because there is only one helper in such situations, I-Help requires a method of selecting an appropriate helper for an individual. We describe the user modelling that takes place in each part of I-Help, in particular to effect this matchmaking for Private Discussions. This modelling takes advantage of a distributed multi-agent architecture, allowing currently relevant user model fragments in various locations to be integrated and computed at the time they are required.

80 citations


Network Information
Related Topics (5)
User interface
85.4K papers, 1.7M citations
89% related
Web page
50.3K papers, 975.1K citations
85% related
Web service
57.6K papers, 989K citations
85% related
Mobile computing
51.3K papers, 1M citations
85% related
Mobile device
58.6K papers, 942.8K citations
83% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202327
202269
2021150
2020167
2019194
2018216