Lw Rutledge

Recommendations based on semantically enriched museum collections

This article presents the CHIP demonstrator for providing personalized access to digital museum collections. It consists of three main components: Art Recommender, Tour Wizard, and Mobile Tour Guide. Based on the semantically enriched Rijksmuseum Amsterdam collection, we show how Semantic Web technologies can be deployed to (partially) solve three important challenges for recommender systems applied in an open Web context: (1) to deal with the complexity of various types of relationships for recommendation inferencing, where we take a content-based approach to recommend both artworks and art-history topics; (2) to cope with the typical user modeling problems, such as cold-start for first-time users, sparsity in terms of user ratings, and the efficiency of user feedback collection; and (3) to support the presentation of recommendations by combining different views like a historical timeline, museum map and faceted browser. Following a user-centered design cycle, we have performed two evaluations with users to test the effectiveness of the recommendation strategy and to compare the different ways for building an optimal user profile for efficient recommendations. The CHIP demonstrator received the Semantic Web Challenge Award (third prize) in 2007, Busan, Korea.

CHIP demonstrator: semantics-driven recommendations and museum tour generation

The main objective of the CHIP project is to demonstrate how Semantic Web technologies can be deployed to provide personalized access to digital museum collections. We illustrate our approach with the digital database ARIA of the Rijksmuseum Amsterdam. For the semantic enrichment of the Rijksmuseum ARIA database we collaborated with the CATCH STITCH project to produce mappings to Iconclass, and with the MultimediaN E-culture project to produce the RDF/OWL of the ARIA and Adlib databases. The main focus of CHIP is on exploring the potential of applying adaptation techniques to provide personalized experience for the museum visitors both on the Web site and in the museum.

Determining user interests about museum collections

Currently, there is an increasing effort to provide various personalized services on museum web sites. This paper presents an approach for determining user interests in a museum collection with the help of an interactive dialog. It uses a semantically annotated collection of the Rijksmuseum Amsterdam to elicit specific users interests in artists, periods, genres and themes and uses these values to recommend relevant artefacts and related concepts from the museum collection. In the presented prototype, we show how constructing a user profile and applying recommender strategies in this way enable dynamical generation personalized museum tours for different users.

Editorial: User interaction in semantic web research

What is semantic web user interaction (SWUI) and why do we want to give it special attention in a journal? Since the first international SWUI workshop at the World Wide Web (WWW) conference in 2004, those of us drawn to this topic have been asking this question. In 2004, the description of the Semantic Web did not have an Interaction Layer on its stack. The concern of developing the Semantic Web seemed entirely on the back end. And yet, the motivating scenario for the Semantic Web postulated in the 2001 Scientific American article was based on what the approach would offer humans. Some of us perceived a disconnect: from our own experience in interaction design, both in research and professional practice, we had seen repeatedly the problems of starting with the technology and assuming that the interaction would take care of itself. Part of our efforts in SWUI was to identify challenges and opportunities for interactions that the semantic web would afford. Consequently, the workshop has been held variously in conjunction with ACMs Conference on Human Factors (CHI), the International Semantic Web Conference, the World Wide Web Conference, and on occasion, co-located between the US and EU. By the third SWUI in 2006, as part of the International Semantic Web Conference, Tim Berners-Lee presented a revised Semantic Web Layer Cake diagram that was now topped with a User Interfaces layer. That was also the workshop where a first critique was presented of what many views onto the Semantic Web looked like at that time: Big Fat Graphs (BFG). The concern of that paper was that it was easy to throw a BFG onto RDF, but what problem did that solve for whom in trying to make use of and sense of information? That question of interfaces to help make sense of semantic data became a theme for SWUI. A few of us looked at data integration challenges and explored what kind of UI paradigm would best enable exploration of the metadata associated with semantic web-based information. Tools like/facet, Topia, mSpace, Haystack, Tabulator and semantic wikis have all been explored at SWUI. In each of these projects the concern has been to bring together multiple data sources in a way that lets users explore, query and represent that information to build new knowledge. An outstanding challenge that remained was how to afford these kinds of explorations over wild data on demand, …

Accuracy in Rating and Recommending Item Features

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 important 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 works 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.