Mark van Setten's research while affiliated with Hogeschool Arnhem and Nijmegen and other places

Publications (22)

Conference Paper
In this paper, we report on a study that explores the contribution of social tags, professional metadata and automatically generated metadata to the retrieval process. In this study, 194 participants tagged a total of 115 videos, while another 140 participants searched the video collection for answers to eight questions. The results show that in th...
Conference Paper
In this paper we present a study in which we explore the potential use of social tagging in providing access to large information systems. Tags are user-supplied access points for information resources, e.g., short labels that characterize pieces of information. As part of long- term research efforts to assess the usefulness of tags for retrieving...
Article
Full-text available
Recommender systems help people to find information that is interesting to them. However, current recommendation techniques only address the user’s short-term and long-term interests, not their immediate interests. This paper describes a method to structure information (with or without using recommendations) taking into account the users’ immediate...
Article
Full-text available
Adaptive systems can be used to help people find their way through large amounts of information by taking into account the content itself and opinions of other people. Annotations that describe content are important in this process as is generally recognized. What is less obviously stated so far is that not only the annotations themselves, but also...
Conference Paper
This workshop intends to bring recommender systems researchers and practitioners together in order to discuss the current state of recommender systems research, both on existing and emerging research topics, and to determine how research in this area should proceed. We are at a pivotal point in recommender systems research where researchers are bot...
Conference Paper
Full-text available
Hybrid recommender systems are capable of providing better rec- ommendations than non-hybrid ones. Our approach to hybrid recommenders is the use of prediction strategies that determine which prediction technique(s) should be used at the moment an actual prediction is required. In this paper, we determine whether case-based reasoning can provide mo...
Conference Paper
Full-text available
This paper describes the context- aware mobile tourist application COMPASS that adapts its services to the user's needs based on both the user's interests and his current context. In order to provide context-aware recommendations, a recommender system has been integrated with a context- aware application platform. We describe how this integration h...
Chapter
To ensure that TV recommender systems become successful, much attention should be paid to the user interface. This chapter describes an iterative design process in which users were involved from the onset. It was performed to design a user interface for a TV recommender system and to develop guidelines for the design of such user interfaces. The fo...
Article
Full-text available
Predicting the interests of a user in information is an important process in personalized information systems. In this paper, we present a way to create prediction engines that allow prediction techniques to be easily combined into prediction strategies. Prediction strategies choose one or a combination of prediction techniques at the moment a pred...
Conference Paper
Full-text available
Interacting with video content can be very time-consuming, and solutions are needed to support people in the process of browsing a video so that they can efficiently interact with the video content. Based on information foraging theory, we have developed a video content browsing tool. Video content is accessed by means of "patches", which provide i...
Conference Paper
Full-text available
An important step in providing personalized information, such as personalized electronic program guides, is predicting the level of interest for a specific user in information, such as TV programs. This paper describes a model that can be used to combine prediction techniques, which predict the level of interest, into prediction strategies. Our hyp...
Conference Paper
This demonstration shows the end-user application of the Video-over-IP (VIP) system. This system encompasses a whole chain of processes for digital video databases, ranging from distributed content production to acquire MPEG-7 metadata (including speech-and video analysis) to the deployment and access to the video database by end users. This system...
Article
Full-text available
This paper describes the use of stylesheets in the search and retrieval process of multimedia information, especially for audiovisual information. For the description of the content of the information, MPEG-7 is used. The use of stylesheets over the MPEG-7 data gives flexibility during both query formulation and the presentation of search results,...
Article
Full-text available
The emerging field of collaborative search and retrieval offers exciting possibilities for both businesses and consumers. This paper sheds insights on several types of information search and retrieval that combines the field of computer supported collaborative work with information search and retrieval. We examine the roots of collaborative search...
Article
In this paper we present guidelines for TV recommender interface design, which we obtained by conducting a design session with a diverse group of TV users. This design session, aiming to explore users' expectations, wishes and demands of user interfaces for TV recommender systems, was conducted as a first step in a user-centered iterative design pr...
Article
Full-text available
The Integrated HealthLog framework and the Physiolog en Sportlog pilot applications demonstrate how multimedia can be used in collaborative settings in healthcare. Patient data can be shared, annotated, discussed and processed by medics involved with a patient. The system is currently piloted in a gait analysis laboratory and in a network of physio...
Article
Personalized information systems try to predict how interested a user is in a piece of information. In this paper, we address this issue not from the prediction algorithm point of view, but by trying to find basic motivations that might convince a user to look at a certain piece of information. This way, we can create better personalized systems th...

Citations

... Several research works on video digital libraries have been proposed so far. Setten and Oltmans [17] propose a distributed search mechanism which retrieves educational videos stored in a database system, using MPEG-7 and Dublin Core metadata. The main drawbacks of this research are related to the focus on a specific application domain. ...
... the meta-data, visual and textual features, and the images themselves over a large scale distributed and heterogeneous system. The article [51] investigates what MPEG-7 means to Multimedia Database systems (MMDBSs) and vice-versa. It is argued that MPEG-7 has to be considered complementary to, rather than competing with, data models employed in it. [52] describes the use of stylesheets ...
... To overcome this issue, video recommendation in cross-network scenario has been proposed [36,48], which is to leverage users' rich cross-network activities to estimate their interests on the video sharing network, showing favorable performance, especially for new users. Generally, video recommendation algorithms for the above two scenarios can be categorized as collaborative ltering based methods [1,17,42], content-based methods [7,9,31,35,57,58], or hybrid methods [4,11,48,56]. The collaborative ltering based methods are to predict a user's ratings of videos based on the preference of other users explicitly or implicitly. ...
... Annotation of tagging and bookmarking Web pages is an example of building a user's profile of preferences implicitly. Annotations can become a part of the user profile as an indication of his/her perspective on the content collection and interest in the annotated object [34]. The tags collected by the user represent part of this user's preferences or interests; hence, this study uses the tag-based user profile as the user's interest in topics of bookmarks in the social bookmarking websites. ...
... determining what programs to record, ordering and filtering electronic program guide (EPG) data and ordering and filtering search results. Personalized selection consists of predicting the level of interest a user will have in a piece of information; adapting the information based on those predictions, such as re-ordering and/or filtering the set of information (Setten, Veenstra & Nijholt, 2002). ...
... Therefore, a collaborative search system has to provide mechanisms to coordinate a combined search of different users. Van Setten & Moelaert---El Hadidy (2000) identify an improved group understanding of a complex search process and the division of labor as the main advantages of collaborative search. ...
... On the other hand, content-based filtering prediction technique is based on descriptive data of recommended items to find items similar to those ones consumed previously, since past interests and tendencies are indicators of future preferences [16]. Barneveld and Setten [26] presented a generic prediction model for a TV recommender system (see Fig. 1). In this model, the prediction technique process calculates a probable interest value of a TV program for a given user, which consists in the item 174 Towards a TV interaction model to elicit user preferences on a recommender system of informative videos prediction (or suggestion). ...
... Referring to the design of rating scales, Swearingen and Sinha (2002) suggested to adopt a mix of different types of questions; Herlocker, Konstan, Terveen, and Riedl (2004) pointed out that an appropriate rating scale should allow users to distinguish among exactly as many levels of liking as it makes sense to them. Van Barneveld and Van Setten (2004) found that most users prefer to have predictions presented by means of 5-star interfaces, while they are less in agreement regarding interfaces to provide input to the system, consistently with the findings of Cena, Vernero, and Gena (2010). Usman, Alghamdi, Tariq, and Puri (2010) proposed a Relative Ranking, where a benchmark item is used to compare other items. ...
... If these or other statistics were not available in the article, we e-mailed authors to see if they have such information that they can send to us. Another 354 studies (19.17% of 1,847 screened articles) were excluded because they did not report sufficient data (e.g., Debuse, Lawley, & Shibl, 2008;van Setten et al., 2006). Third, the article had to provide an independent dataset . ...
... Consequently, it may not be easy for them to evaluate the proposed recommendation. Hence, various researchers have tried to understand the factors that lead to the acceptance of a recommendation by a given user [105, 30, 24, 97, 33]. [105] was among the first to point out that the effectiveness of a RS is dependent on factors that go beyond the quality of the prediction algorithm. ...