User modeling

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

Communication link system based on user indicator

Abstract: A system, method, and processor readable medium containing code embodied therein are provided that enable system users to view one or more system user's status and to establish communications with the one or more system users using a user indicator in an electronic document (e.g., electronic mail message, hypertext markup language document). The user indicator may be a system user's login identification presented as a hypertext link to one or more communication options. The system may include an identification module for identifying the one or more system users. The identification module may identify a system user's login identification (e.g., the system user's name, employee number) and provide the system user's status using the user indicator. A status module, responsive to the identification module, provides the status of the system users. The status module may provide a visual indication of a system user's status using, for example, color coding, formatting, symbols, etc. A communication module for establishing a communication link with the one or more system users using the user indicator may also be provided. The communication module may be used to establish a variety of communications with one or more of the system users. For example, a user may chat, telephone, transmit an electronic mail message, share one or more application programs (e.g., whiteboard presentations), fax, or page one or more of the system users by selecting (e.g., by using a conventional computer mouse or keyboard) the communication desired using user indicator.

A Comparison of Offline Evaluations, Online Evaluations, and User Studies in the Context of Research-Paper Recommender Systems

Abstract: The evaluation of recommender systems is key to the successful application of recommender systems in practice. However, recommender-systems evaluation has received too little attention in the recommender-system community, in particular in the community of research-paper recommender systems. In this paper, we examine and discuss the appropriateness of different evaluation methods, i.e. offline evaluations, online evaluations, and user studies, in the context of research-paper recommender systems. We implemented different content-based filtering approaches in the research-paper recommender system of Docear. The approaches differed by the features to utilize (terms or citations), by user model size, whether stop-words were removed, and several other factors. The evaluations show that results from offline evaluations sometimes contradict results from online evaluations and user studies. We discuss potential reasons for the non-predictive power of offline evaluations, and discuss whether results of offline evaluations might have some inherent value. In the latter case, results of offline evaluations were worth to be published, even if they contradict results of user studies and online evaluations. However, although offline evaluations theoretically might have some inherent value, we conclude that in practice, offline evaluations are probably not suitable to evaluate recommender systems, particularly in the domain of research paper recommendations. We further analyze and discuss the appropriateness of several online evaluation metrics such as click-through rate, link-through rate, and cite-through rate.

Method and system of user authentication with bioresponse data

Abstract: In one exemplary embodiment, a computer-implemented method includes the step of providing an image to a user. The image is provided with a computer display, An eye-tracking data is obtained from the user when the user views the image. The eye-tracking data is obtained with an eye-tracking system. A user attribute is determined based on the eye-tracking data. The user is enabled to access a digital resource when the user attribute is associated with a permission to access the digital resource. The user attribute can be a personhood state. The digital resource can be a web page document. An instruction can be provided to the user regarding a pattern of viewing the image. The pattern of viewing the image can include instructing the user to gaze on a specified sequence of image elements.

Generation and acceptance of tailored offers

Abstract: A system for generating and presenting an offer tailored to a particular user. Information about the user is collected from multiple properties. The information is used to generate tailored offers to the user. The offers are presented to the user. The user easily accepts desired offers.

A Mixed Approach to Modelling Learning Styles in Adaptive Educational Hypermedia

Abstract: In this paper we present a theoretical framework that deals with the dynamic modeling of learning styles. In that sense we propose a mixed approach. Firstly, we collect explicit information about the students by means of the ILS (Index of Learning Styles) questionnaire developed by Felder and Soloman. Our system adapts the course structure and sequencing to the student’s profile. Later, we use the implicit information gathered by the system during the course in order to dynamically modify or not the course structure and sequencing previously selected. As the amount of data available for a particular student grows, the learning profile of students may or may not change. We believe that improving learning process implies not only acquisition of knowledge but also a good level of satisfaction and motivation of learners. Incorporation of learning styles into the user model is a good way to take into account student’s preferences, and it could be integrated and modified in a more complex framework.