Topic
User modeling
About: User modeling is a research topic. Over the lifetime, 10701 publications have been published within this topic receiving 278012 citations.
Papers published on a yearly basis
Papers
More filters
Patent•
05 Jun 2011
TL;DR: In this article, a method of providing role-based game play on a social computer network was proposed, where user inputs are received via a computer network from user computers, and these inputs are stored in a memory, and at least a portion of the memory is located away from the user computers.
Abstract: The present invention is a method of providing role based game play on a social computer network. User inputs are received via a computer network from user computers. These inputs are stored in a memory, and at least a portion of the memory is located away from the user computers. A group of two or more characters for a single user are created based on inputs from a user. One or more of these characters is associated with a friend user on the social computer network. At least a portion of information related to an outcome from the game is displayed on a device of the single user. Finally, the single user controls all the inputs for the actions of their characters during the game.
94 citations
Patent•
14 Mar 1997
TL;DR: A graphical user interface for a computer program includes the representation of a face (an avatar) on a computer screen which allows a user to communicate the user's attitude to a situation represented by the computer program as discussed by the authors.
Abstract: A graphical user interface for a computer program includes the representation of a face (an avatar) on a computer screen which allows a user to communicate the user's attitude to a situation represented by the computer program. The expression of the face changes according to the user's movement of a cursor over the face. In response to a situation appearing on the computer screen, the user sets the expression on the face to correspond with the user's attitude. The situation on the computer screen changes accordingly.
94 citations
TL;DR: A document clustering algorithm that carries out incremental, unsupervised concept learning over Web documents in order to acquire user profiles, named WebDCC (Web Document Conceptual Clustering), that offers comprehensible clustering solutions that can be easily interpreted and explored by both users and other agents.
94 citations
06 Nov 2006
TL;DR: This work demonstrates that the Bayesian modeling approach effectively trades off between shared and user-specific information, alleviating poor initial performance for each user and finds that implicit feedback has very limited unstable predictive value by itself and only marginal value when combined with explicit feedback.
Abstract: Research in information retrieval is now moving into a personalized scenario where a retrieval or filtering system maintains a separate user profile for each user. In this framework, information delivered to the user can be automatically personalized and catered to individual user's information needs. However, a practical concern for such a personalized system is the "cold start problem": any user new to the system must endure poor initial performance until sufficient feedback from that user is provided.To solve this problem, we use both explicit and implicit feedback to build a user's profile and use Bayesian hierarchical methods to borrow information from existing users. We analyze the usefulness of implicit feedback and the adaptive performance of the model on two data sets gathered from user studies where users' interaction with a document, or implicit feedback, were recorded along with explicit feedback. Our results are two-fold: first, we demonstrate that the Bayesian modeling approach effectively trades off between shared and user-specific information, alleviating poor initial performance for each user. Second, we find that implicit feedback has very limited unstable predictive value by itself and only marginal value when combined with explicit feedback.
93 citations
01 Dec 2005
TL;DR: The results show that the performance and characteristics of the strategy are in fact highly dependent on the user model, and raises significant doubts about the current practice of learning and evaluating strategies with the same user model.
Abstract: Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely evaluated in actual user trials and it remains unclear how the choice of user model affects the quality of the learned strategy. In particular, the degree to which strategies learned with a user model generalise to real user populations has not be investigated. This paper presents a series of experiments that qualitatively and quantitatively examine the effect of the user model on the learned strategy. Our results show that the performance and characteristics of the strategy are in fact highly dependent on the user model. Furthermore, a policy trained with a poor user model may appear to perform well when tested with the same model, but fail when tested with a more sophisticated user model. This raises significant doubts about the current practice of learning and evaluating strategies with the same user model. The paper further investigates a new technique for testing and comparing strategies directly on real human-machine dialogues, thereby avoiding any evaluation bias introduced by the user model
93 citations