Interest based selection of user generated content for rich communication services

Abstract

The last few years, we have witnessed an exponential growth in available content, much of which is user generated (e.g. pictures, videos, blogs, reviews, etc.). The downside of this overwhelming amount of content is that it becomes increasingly difficult for users to identify the content they really need, resulting into considerable research efforts concerning personalised search and content retrieval.On the other hand, this enormous amount of content raises new possibilities: existing services can be enriched using this content, provided that the content items used match the user's personal interests. Ideally, these interests should be obtained in an automatic, transparent way for an optimal user experience.In this paper two models representing user profiles are presented, both based on keywords and with the goal to enrich real-time communication services. The first model consists of a light-weight keyword tree which is very fast, while the second approach is based on a keyword ontology containing extra temporal relationships to capture more details of the user's behavior, however exhibiting lower performance. The profile models are supplemented with a set of algorithms, allowing to learn user interests and retrieving content from personal content repositories.In order to evaluate the performance, an enhanced instant messaging communication service was designed. Through simulations the two models are assessed in terms of real-time behavior and extensibility. User evaluations Preprint submitted to Journal of Network and Computer Applications October 26, 2009 allow to estimate the added value of the approach taken. The experiments conducted indicate that the algorithms succeed in retrieving content matching the user's interests and both models exhibit a linear scaling behavior. The algorithms perform clearly better in finding content matching several user interests when benefiting from the extra temporal information in the ontology based model.

Hybrid reasoning technique for improving context-aware applications

“…As already shown in (Strobbe et al, 2010), this figure also illustrates the added value of the extra usedTogether and comesNext relationships in the ontology keyword model. The results are clearly better than for the tree based model.…”

“…To represent the user interests we developed two keyword models (Strobbe et al, 2010): a simple keyword tree and a more expressive keyword ontology. In both approaches keywords are modeled using a tree structure with keywords representing main categories on top and subcategories and specific interests lower in the tree.…”

“…In general, each relationship u i,j connects node n i,x with node n j,y and has also an associated weight value w u i,j between 0 and 1 indicating the strength of the relationship. Figure 15Designed ontology for the enhanced instant messaging use casefigure.15 shows the ontology used for this use case, which is an extended version of the ontology we presented in (Strobbe et al, 2010). Additional personal and context information about the user is modeled: his home and work address, his current location, a presence status based on the location of the user and the time of the day.…”

“…More details about the designed algorithms and the used formulas can be found in (Strobbe et al, 2010).…”

“…CASP collects context information in a certain domain, facilitating the development of new services in that domain. CASP has already been used in diverse application areas ( (Strobbe et al, 2007), (Ongenae et al, 2008), (Strobbe et al, 2010) ), and is described in more detail in section 3Architecturesection.3.…”