User modeling

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

Systems and methods for providing targeted information in the context of electronic gaming

Abstract: A system and method for providing information to a user in the context of an online game, in which game units are allocated to the user. The system and method include acquiring user profile data relating to at least one of personal characteristic of the user, retrieving information items from a database based on the user profile data, associating the information items with the game units allocated to the user, and presenting the game units to the user with the information items displayed on the game units.

Implicit user profiling for on demand relevance feedback

Abstract: In the area of information retrieval and information filtering, relevance feedback is a popular technique which searches similar documents based on the documents browsed by the user. If the user wants to conduct relevance feedback on demand, which means the user wants to see similar documents while reading a document, the existing user profiling techniques cannot acquire keywords in high precision that the user is interested in at such a short time. This paper proposes a method for extracting text parts which the user might be interested in from the whole text of the Web page based on the user's mouse operation in the Web browser. The objective of this research is to (1) find what kind of mouse operation represent users' interests, (2) see the effectiveness of the found mouse operation in selecting keywords, and (3) compare our method with tf-idf, which is the most fundamental method used in many user profiling systems. From the user experiment, the precision to select keywords of our method is about 1.4 times compared with that of tf-idf.

Recommendation Based Process Modeling Support: Method and User Experience

Abstract: Although most workflow management systems nowadays offer graphical editors for process modeling, the learning curve is still too steep for users who are unexperienced in process modeling. The efficiency of users may decrease when starting process modeling with minimal expertise and no obvious modeling support. This paper describes the first contribution towards a theoretically sound and empirically validated analysis of a recommender-based modeling support who is geared towards both novices and expert users. The idea is to interpret process descriptions as tags which describe the intention of the process. This leads us to the notion of virtual documents or signatures. Based on these signatures we provide a search interface to process models stored in a repository. Additionally the user can invoke a recommendation function during modeling time and the system automatically identifies and suggests relevant process fragments. By adding two additional criteria, the frequency of process reuse and structural correctness, we arrive at a full-fledged modeling support system, which provides an easy to use interface to the user while retaining a high fidelity to the user's modeling intentions. We validated our support system with a user experiment based on real-life process models and our prototype implementation.

Web montage: a dynamic personalized start page

Abstract: Despite the connotation of the words "browsing" and "surfing," web usage often follows routine patterns of access. However, few mechanisms exist to assist users with these routine tasks; bookmarks or portal sites must be maintained manually and are insensitive to the user's browsing context. To fill this void, we designed and implemented the montage system. A web montage is an ensemble of links and content fused into a single view. Such a coalesced view can be presented to the user whenever he or she opens the browser or returns to the start page. We pose a number of hypotheses about how users would interact with such a system, and test these hypotheses with a fielded user study. Our findings support some design decisions, such as using browsing context to tailor the montage, raise questions about others, and point the way toward future work.

All Work and No Play

Abstract: Many conversational agents (CAs) are developed to answer users' questions in a specialized domain. In everyday use of CAs, user experience may extend beyond satisfying information needs to the enjoyment of conversations with CAs, some of which represent playful interactions. By studying a field deployment of a Human Resource chatbot, we report on users' interest areas in conversational interactions to inform the development of CAs. Through the lens of statistical modeling, we also highlight rich signals in conversational interactions for inferring user satisfaction with the instrumental usage and playful interactions with the agent. These signals can be utilized to develop agents that adapt functionality and interaction styles. By contrasting these signals, we shed light on the varying functions of conversational interactions. We discuss design implications for CAs, and directions for developing adaptive agents based on users' conversational behaviors.