HCI Bibliography Home | HCI Journals | About UMUAI | Journal Info | UMUAI Journal Volumes | Detailed Records | RefWorks | EndNote | Hide Abstracts
UMUAI Tables of Contents: 040506070809101112131415161718192021222324

User Modeling and User-Adapted Interaction 14

Editors:Alfred Kobsa
Standard No:ISSN 0924-1868 (print) EISSN 1573-1391 (online)
Links:link.springer.com | Table of Contents
  1. UMUAI 2004-02 Volume 14 Issue 1
  2. UMUAI 2004-06 Volume 14 Issue 2/3
  3. UMUAI 2004 Volume 14 Issue 4
  4. UMUAI 2004 Volume 14 Issue 5

UMUAI 2004-02 Volume 14 Issue 1

Preface: Special Issue on User Modeling and Personalization for Television BIBFull-Text 1-3
  Liliana Ardissono; Mark Maybury
Improving the Quality of the Personalized Electronic Program Guide BIBAKFull-Text 5-36
  Derry O'Sullivan; Barry Smyth
As Digital TV subscribers are offered more and more channels, it is becoming increasingly difficult for them to locate the right programme information at the right time. The personalized Electronic Programme Guide (pEPG) is one solution to this problem; it leverages artificial intelligence and user profiling techniques to learn about the viewing preferences of individual users in order to compile personalized viewing guides that fit their individual preferences. Very often the limited availability of profiling information is a key limiting factor in such personalized recommender systems. For example, it is well known that collaborative filtering approaches suffer significantly from the sparsity problem, which exists because the expected item-overlap between profiles is usually very low. In this article we address the sparsity problem in the Digital TV domain. We propose the use of data mining techniques as a way of supplementing meagre ratings-based profile knowledge with additional item-similarity knowledge that can be automatically discovered by mining user profiles. We argue that this new similarity knowledge can significantly enhance the performance of a recommender system in even the sparsest of profile spaces. Moreover, we provide an extensive evaluation of our approach using two large-scale, state-of-the-art online systems -- PTVPlus, a personalized TV listings portal and Físchlár, an online digital video library system.
Keywords: case-based reasoning; collaborative filtering; data mining; digital TV; personalization; similarity maintenance
Group Modeling: Selecting a Sequence of Television Items to Suit a Group of Viewers BIBAKFD 37-85
  Judith Masthoff
Watching television tends to be a social activity. So, adaptive television needs to adapt to groups of users rather than to individual users. In this paper, we discuss different strategies for combining individual user models to adapt to groups, some of which are inspired by Social Choice Theory. In a first experiment, we explore how humans select a sequence of items for a group to watch, based on data about the individuals' preferences. The results show that humans use some of the strategies such as the Average Strategy (a.k.a. Additive Utilitarian), the Average Without Misery Strategy and the Least Misery Strategy, and care about fairness and avoiding individual misery. In a second experiment, we investigate how satisfied people believe they would be with sequences chosen by different strategies, and how their satisfaction corresponds with that predicted by a number of satisfaction functions. The results show that subjects use normalization, deduct misery, and use the ratings in a non-linear way. One of the satisfaction functions produced reasonable, though not completely correct predictions. According to our subjects, the sequences produced by five strategies give satisfaction to all individuals in the group. The results also show that subjects put more emphasis than expected on showing the best rated item to each individual (at a cost of misery for another individual), and that the ratings of the first and last items in the sequence are especially important. In a final experiment, we explore the influence viewing an item can have on the ratings of other items. This is important for deciding the order in which to present items. The results show an effect of both mood and topical relatedness.
Keywords: adaptation; group modeling; interactive television; recommender; social choice
Categorization of Japanese TV Viewers Based on Program Genres They Watch BIBAKDF 87-117
  Yumiko Hara; Yumiko Tomomune; Maki Shigemori
Although programpreferences can be characterized on the basis of demographic attributes like sex, age or occupation or by taking the cultural studies approach focused on ethnic or social traits, preferences for programs often differ among people of the same sex, age, occupation and social class. We think that nothing can describe subjects' viewing preferences more accurately than what programs they had watched in the past. To verify our hypothesis, we surveyed the viewing behavior of more than 1,600 randomly chosen individuals, and utilized this data to analyze people's program choices. We categorized the respondents by the similarity of the programs they had watched and examined the groupings that emerged and the features of these groups.
   From our analysis, it became clear that a 'more/less serious' and 'more/less fictional' axes are involved in program selection.
   Our results show that eight groups (stereotypes) explain viewers' contact with television, their motivation for choosing programs to watch, and their interest in matters other than television. Applying these stereotypes to the process of program selection or recommendation will be useful for the future design of personalized adaptive systems.
Keywords: audience segmentation; Japan; personalized TV; program genre; stereotype; TV; user study; viewer; viewing preference
Personalcasting: Tailored Broadcast News BIBAKEB 119-144
  Mark Maybury; Warren Greiff; Stanley Boykin
Broadcast news sources and newspapers provide society with the vast majority of real-time information. Unfortunately, cost efficiencies and real-time pressures demand that producers, editors, and writers select and organize content for stereotypical audiences. In this article we illustrate how content understanding, user modeling, and tailored presentation generation promise personalcasts on demand. Specifically, we report on the design and implementation of a personalized version of a broadcast news understanding system, MITRE's Broadcast News Navigator (BNN), that tracks and infers user content interests and media preferences. We report on the incorporation of Local Context Analysis to both expand the user's original query to the most related terms in the corpus, as well as to allow the user to provide interactive feedback to enhance the relevance of selected newsstories. We describe an empirical study of the search for stories on ten topics from a video corpus. By personalizing both the selection of stories and the form in which they are delivered, we provide users with tailored broadcast news. This individual news personalization provides more fine-grained content tailoring than current personalized television program level recommenders and does not rely on externally provided program metadata.
Keywords: broadcast news; personalization; query expansion; relevance feedback; story selection; user modeling

UMUAI 2004-06 Volume 14 Issue 2/3

Preface to Special Issue on User Modeling for Web Information Retrieval BIBDD 147-157
  Peter Brusilovsky; Carlo Tasso
Anatomy and Empirical Evaluation of an Adaptive Web-Based Information Filtering System BIBAKFull-Text 159-200
  Alessandro Micarelli; Filippo Sciarrone
A case study in adaptive information filtering systems for the Web is presented. The described system comprises two main modules, named HUMOS and WIFS. HUMOS is a user modeling system based on stereotypes. It builds and maintains long term models of individual Internet users, representing their information needs. The user model is structured as a frame containing informative words, enhanced with semantic networks. The proposed machine learning approach for the user modeling process is based on the use of an artificial neural network for stereotype assignments. WIFS is a content-based information filtering module, capable of selecting html/text documents on computer science collected from the Web according to the interests of the user. It has been created for the very purpose of the structure of the user model utilized by HUMOS. Currently, this system acts as an adaptive interface to the Web search engine ALTA VISTATM. An empirical evaluation of the system has been made in experimental settings. The experiments focused on the evaluation, by means of a non-parametric statistics approach, of the added value in terms of system performance given by the user modeling component; it also focused on the evaluation of the usability and user acceptance of the system. The results of the experiments are satisfactory and support the choice of a user model-based approach to information filtering on the Web.
Keywords: artificial neural networks; case-based reasoning; empirical methods; information filtering; user modeling
User Involvement in Automatic Filtering: An Experimental Study BIBAKFull-Text 201-237
  Annika Wærn
The aim in information filtering is to provide users with a personalised selection of information, based on their interest profile. In adaptive information filtering, this profile partially or completely acquired by automatic means. This paper investigates if profile generation can be partially acquired by automatic methods and partially by direct user involvement. The issue is explored through an empirical study of a simulated filtering system that mixes automatic and manual profile generation. The study covers several issues involved in mixed control. The first issue concerns if a machine-learned profile can provide better filtering performance if generated from an initial explicit user profile. The second issue concerns if user involvement can improve on a system-generated or adapted profile. Finally, the relationship between filtering performance and user ratings is investigated. In this particular study the initial setup of a personal profile was effective and yielded performance improvements that persisted after substantiate training. However, the study showed no correlation between users' ratings of profiles and profile filtering performance, and only weak indications that users could improve profiles that already had been trained on feedback.
Keywords: experimental study; information filtering; personal profile; recommender systems; user involvement
User Modelling for News Web Sites with Word Sense Based Techniques BIBAKFull-Text 239-257
  Bernardo Magnini; Carlo Strapparava
SiteIF is a personal agent for a bilingual news web site that learns user's interests from the requested pages. In this paper we propose to use a word sense based document representation as a starting point to build a model of the user's interests. Documents passed over are processed and relevant senses (disambiguated over WordNet) are extracted and then combined to form a semantic network. A filtering procedure dynamically predicts new documents on the basis of the semantic network.
   There are two main advantages of a sense-based approach: first, the model predictions, being based on senses rather than words, are more accurate; second, the model is language independent, allowing navigation in multilingual sites. We report the results of a comparative experiment that has been carried out to give a quantitative estimation of these improvements.
Keywords: adaptive hypermedia; content-based user modelling; natural language processing; WORDNET
Interactive Information Retrieval Using Clustering and Spatial Proximity BIBAKFull-Text 259-288
  Anton Leuski; James Allan
A web-based search engine responds to a user's query with a list of documents. This list can be viewed as the engine's model of the user's idea of relevance -- the engine 'believes' that the first document is the most likely to be relevant, the second is slightly less likely, and so on. We extend this idea to an interactive setting where the system accepts the user's feedback and adjusts its relevance model. We develop three specific models that are integrated as part of a system we call Lighthouse. The models incorporate document clustering and a spring-embedding visualization of inter-document similarity. We show that if a searcher were to use Lighthouse in ways consistent with the model, the expected effectiveness improves -- i.e., the relevant documents are found more quickly in comparison to existing methods.
Keywords: clustering; information organization; information retrieval; information visualization

UMUAI 2004 Volume 14 Issue 4

A Framework for the Initialization of Student Models in Web-based Intelligent Tutoring Systems BIBAKCC 289-316
  Victoria Tsiriga; Maria Virvou
Initializing a student model for individualized tutoring in educational applications is a difficult task, since very little is known about a new student. On the other hand, fast and efficient initialization of the student model is necessary. Otherwise the tutoring system may lose its credibility in the first interactions with the student. In this paper we describe a framework for the initialization of student models in Web-based educational applications. The framework is called ISM. The basic idea of ISM is to set initial values for all aspects of student models using an innovative combination of stereotypes and the distance weighted k-nearest neighbor algorithm. In particular, a student is first assigned to a stereotype category concerning her/his knowledge level of the domain being taught. Then, the model of the new student is initialized by applying the distance weighted k-nearest neighbor algorithm among the students that belong to the same stereotype category with the new student. ISM has been applied in a language learning system, which has been used as a test-bed. The quality of the student models created using ISM has been evaluated in an experiment involving classroom students and their teachers. The results from this experiment showed that the initialization of student models was improved using the ISM framework.
Keywords: initialization; machine learning for user modeling; stereotypes; student modeling; Web-based intelligent tutoring systems
Empirical Derivation of a Sequence of User Stereotypes for Language Learning BIBAKFull-Text 317-350
  Lisa N. Michaud; Kathleen F. McCoy
The work described here pertains to ICICLE, an intelligent tutoring system for which we have designed a user model to supply data for intelligent natural language parse disambiguation. This model attempts to capture the user's mastery of various grammatical units and thus can be used to predict the grammar rules he or she is most likely using when producing language. Because ICICLE's user modeling component must infer the user's language mastery on the basis of limited writing samples, it makes use of an inferencing mechanism that will require knowledge of stereotypic acquisition sequences in the user population. We discuss in this paper the methodology of how we have applied an empirical investigation into user performance in order to derive the sequence of stereotypes that forms the basis of our modeling component's reasoning capabilities.
Keywords: CALL; empirical analysis; ITS; NLP; parse disambiguation; student modeling; stereotypes
Computational Modeling and Analysis of Knowledge Sharing in Collaborative Distance Learning BIBAKFull-Text 351-381
  Amy Soller
This research aims to support collaborative distance learners by demonstrating how a probabilistic machine learning method can be used to model and analyze online knowledge sharing interactions. The approach applies Hidden Markov Models and Multidimensional Scaling to analyze and assess sequences of coded online student interaction. These analysis techniques were used to train a system to dynamically recognize (1) when students are having trouble learning the new concepts they share with each other, and (2) why they are having trouble. The results of this research may assist an instructor or intelligent coach in understanding and mediating situations in which groups of students collaborate to share their knowledge.
Keywords: computer-supported collaborative learning; interaction analysis; knowledge sharing; dialog; hidden Markov models

UMUAI 2004 Volume 14 Issue 5

Exploiting Query Repetition and Regularity in an Adaptive Community-Based Web Search Engine BIBAKFull-Text 383-423
  Barry Smyth; Evelyn Balfe; Jill Freyne
Search engines continue to struggle with the challenges presented by Web search: vague queries, impatient users and an enormous and rapidly expanding collection of unmoderated, heterogeneous documents all make for an extremely hostile search environment. In this paper we argue that conventional approaches to Web search -- those that adopt a traditional, document-centric, information retrieval perspective -- are limited by their refusal to consider the past search behaviour of users during future search sessions. In particular, we argue that in many circumstances the search behaviour of users is repetitive and regular; the same sort of queries tend to recur and the same type of results are often selected. We describe how this observation can lead to a novel approach to a more adaptive form of search, one that leverages past search behaviours as a means to re-rank future search results in a way that recognises the implicit preferences of communities of searchers. We describe and evaluate the I-SPY search engine, which implements this approach to collaborative, community-based search. We show that it offers potential improvements in search performance, especially in certain situations where communities of searchers share similar information needs and use similar queries to express these needs. We also show that I-SPY benefits from important advantages when it comes to user privacy. In short, we argue that I-SPY strikes a useful balance between search personalization and user privacy, by offering a unique form of anonymous personalization, and in doing so may very well provide privacy-conscious Web users with an acceptable approach to personalized search.
Keywords: Meta search; personalization; social search; Web search
Knowledge Discovery with Genetic Programming for Providing Feedback to Courseware Authors BIBAKFull-Text 425-464
  Cristóbal Romero; Sebastián Ventura
We introduce a methodology to improve Adaptive Systems for Web-Based Education. This methodology uses evolutionary algorithms as a data mining method for discovering interesting relationships in students' usage data. Such knowledge may be very useful for teachers and course authors to select the most appropriate modifications to improve the effectiveness of the course. We use Grammar-Based Genetic Programming (GBGP) with multi-objective optimization techniques to discover prediction rules. We present a specific data mining tool that can help non-experts in data mining carry out the complete rule discovery process, and demonstrate its utility by applying it to an adaptive Linux course that we developed.
Keywords: adaptive system for web-based education; data mining; evolutionary algorithms; grammar-based genetic programming; prediction rules