User models: theory, method, and practice (original) (raw)
Related papers
User modeling for adaptive news access
2000
We present a framework for adaptive news access, based on machine learning techniques speci¢cally designed for this task. First, we focus on the system's general functionality and system architecture.We then describe the interface and design of two deployed news agents that are part of the described architecture. While the ¢rst agent provides personalized news through a web-based interface, the second system is geared towards wireless information devices such as PDAs (personal digital assistants) and cell phones. Based on implicit and explicit user feedback, our agents use a machine learning algorithm to induce individual user models. Motivated by general shortcomings of other user modeling systems for Information Retrieval applications, as well as the speci¢c requirements of news classi¢cation, we propose the induction of hybrid user models that consist of separate models for short-term and long-term interests. Furthermore, we illustrate how the described algorithm can be used to address an important issue that has thus far received little attention in the Information Retrieval community: a user's information need changes as a direct result of interaction with information.We empirically evaluate the system's performance based on data collected from regular system users. The goal of the evaluation is not only to understand the performance contributions of the algorithm's individual components, but also to assess the overall utility of the proposed user modeling techniques from a user perspective. Our results provide empirical evidence for the utility of the hybrid user model, and suggest that effective personalization can be achieved without requiring any extra effort from the user.
Evaluating a user-model based personalisation architecture for digital news services
2000
An architecture that provides personalised filtering and dissemination of news items is presented. It is based on user profiles and it provides mechanisms that allow the user to control and tailor to his own needs the interaction between three different sources of relevance judgements: the existing newspaper categorisation by sections, basic information retrieval on user selected keywords, and an additional operation of automatic categorisation against an alternative hierarchy of categories. These three tiers cover some of the most promising access methods for digital libraries. The proposed architecture has been implemented and evaluation results are presented, covering user response, system efficiency, and user preferences regarding the set of methods made available to them.
Adaptive user modeling for filtering electronic news
System Sciences, 2002. …, 2002
A prototype system for the fine-grained filtering of news items has been developed and a pilot test has been conducted. The system is based on an adaptive user model that integrates stereotypes and artificial neural networks. The stereotypes are based on newspaper sections and sub-...
User models in information filtering
1994
Individuals scanning information channels and filtering these according to their needs performs according to cultural and organizational psychosocial factors as well as their psychological profile, hiding their motives for selecting information. The aim is here to explore these aspects in order to understand and to improve the quality of a information selection process.
A user model based on content analysis for the intelligent personalization of a news service
2001
Abstract In this paper we present a methodology designed to improve the intelligent personalization of news services. Our methodology integrates textual content analysis tasks to achieve an elaborate user model, which represents separately short-term needs and long-term multi-topic interests. The characterization of user's interests includes his preferences about content, using a wide coverage and non-specific-domain classification of topics, and structure (newspaper sections).
Sections, categories and keywords as interest specification tools for personalised news services
Online Information Review, 2001
Through a evaluation of system performance and user satisfaction for the Mercurio system -a system that sends personalised news selections via email -, the general applicability and usefulness of different methods of specifying user interest (sections, categories and keywords) are considered for the general case of digital news services. The specific characteristics distinguishing such systems from more general information systems are outlined and their effect is discussed. An evaluation blueprint for them is proposed starting from information retrieval procedures, existing work on search engine evaluation, and a close study of the working principles and the required evaluation according to the particular properties and conditions of the services under consideration. Actual evaluation results for system tests based both on real users and custom tailored test cases are presented and discussed. Conclusions cover the nature of the information handling tasks that digital news services are faced with, the relative merits of sections, categories, and key words with respect to this particular set of tasks, and the risks of careless application of recall and precision measures in systems such as these.
User modeling is the key element in assisting intelligence analysts to meet the challenge of gathering relevant information from the massive amounts of available data. We have developed a dynamic user model to predict the analyst's intent and help the information retrieval application better serve the analyst's information needs. In order to justify the effectiveness of our user modeling approach, we have conducted a user evaluation study with actual end user, three working intelligence analysts, and compared our user model enhanced information retrieval system with a commercial off-the-shelf system, the Verity Query Language. We describe our experimental setup and the specific metrics essential to evaluate user modeling for information retrieval. The results show that our user modeling approach tracked individual's interests, adapted to their individual searching strategies, and helped retrieve more relevant documents than the Verity Query Language system.
Context and Interest Fluctuations in User Profiles for News Filtering
math.uaa.alaska.edu
This work examined the issue of accuracy in modeling users within the task of browsing Usenet newsgroups. Two experiments were conducted. In the first experiment, subjects were presented with a series of news articles and asked to browse the articles and read those that appeared interesting. After reading an article, subjects ranked each article as being of interest, disinterest, or ambivalent. Upon completion of the browsing phase, subjects then read and classified all articles. In the second experiment, the same task was performed except subjects were split into two groups. Articles were displayed to the first group as in the first experiment, but articles were displayed to the second group with additional context in the form of a line of text from the body of the article. The experimental results indicate that the current system of browsing results in many messages that users do not read, but would be interested in reading. Furthermore, the addition of a line of text for context helped users differentiate among articles of disinterest better than if the text was not provided. Finally, the results indicate that users often change their mind about whether they like or dislike a particular article. These results suggest that a news filter would be a great aid in finding articles likely to be of interest that are normally missed. However, the accuracy of such a filter will be limited due to human inconsistencies. Complementary techniques such as data visualization should also be explored to better facilitate filtering by humans.