Friday 1 August, 11:00 - 12:30Chair: Geert-Jan Houben
Accuracy in Rating and Recommending Item Features (page 163)Lloyd Rutledge, Natalia Stash, Yiwen Wang, and Lora Aroyo
This paper discusses accuracy in processing ratings of and recommendations for item features. Such processing facilitates feature-based user navigation in recommender system interfaces. Item features, often in the form of tags, categories or meta-data, are becoming impor- tant hypertext components of recommender interfaces. Recommending features would help unfamiliar users navigate in such environments. This work explores techniques for improving feature recommendation accuracy. Conversely, it also examines possibilities for processing user ratings of features to improve recommendation of both features and items. This work's illustrative implementation is a web portal for a museum collection that lets users browse, rate and receive recommendations for both artworks and interrelated topics about them. Accuracy measurements compare proposed techniques for processing feature ratings and recommending features. Resulting techniques recommend features with relative accuracy. Analysis indicates that processing ratings of either features or items does not improve accuracy of recommending the other.
Using Collaborative Models to Adaptively Predict Visitor Locations in Museums (page 42)Fabian Bohnert, Ingrid Zukerman, Shlomo Berkovsky, Timothy Baldwin, and Liz Sonenberg
The vast amounts of information presented in museums can be overwhelming to a visitor, whose receptivity and time are typically limited. Hence, s/he might have difficulties selecting interesting exhibits to view within the available time. Mobile, context-aware guides oer the opportunity to improve a visitor's experience by recommending exhibits of interest, and personalising the delivered content. The first step in this recommendation process is the accurate prediction of a visitor's activities and preferences. In this paper, we present two adaptive collaborative models for predicting a visitor's next locations in a museum, and an ensemble model that combines their predictions. Our experimental results from a study using a small dataset of museum visits are encouraging, with the ensemble model yielding the best performance overall.
Pervasive Personalisation of Location Information: Personalised Context Ontology (page 143)William T. Niu and Judy Kay
There is considerable value in personalising information about people's location. Personalised Context Ontology (PECO) is an ontology for a building, and with PECO, we can provide personalised descriptions of the relevant people. For pragmatic reasons, it is important that PECO is created semi-automatically, making exible use of a range of sources. For reasons of user control, it is important that PECO can be used to explain the personalisation. This paper describes PECO and how it is created for reasoning about a building. We also describe its use in an application called Locator, which presents information about the people in a building. PECO enables Locator to provide personalised information in two ways: it shows people of relevance and it makes use of personalised location labels. At the same time, PECO enables the user to scrutinise the reasoning about the personalisation. We report a study with eight users in which we compare a personalised and a non-adaptive versions of Locator. This indicates that people preferred the personalised version even though they could complete the designed tasks with both systems.