HCI Bibliography Home | HCI Journals | About UMUAI | Journal Info | UMUAI Journal Volumes | Detailed Records | RefWorks | EndNote | Hide Abstracts
UMUAI Tables of Contents: 09101112131415161718192021222324

User Modeling and User-Adapted Interaction 19

Editors:Alfred Kobsa
Standard No:ISSN 0924-1868 (print) EISSN 1573-1391 (online)
Links:link.springer.com | Table of Contents
  1. UMUAI 2009-02 Volume 19 Issue 1/2
  2. UMUAI 2009-08 Volume 19 Issue 3
  3. UMUAI 2009-10 Volume 19 Issue 4
  4. UMUAI 2009-12 Volume 19 Issue 5

UMUAI 2009-02 Volume 19 Issue 1/2

Special Issue on Data Mining for Personalization

Preface to the special issue on data mining for personalization BIBFull-Text 1-3
  Bamshad Mobasher; Alexander Tuzhilin
Search personalization through query and page topical analysis BIBAKFull-Text 5-33
  Sofia Stamou; Alexandros Ntoulas
Thousands of users issue keyword queries to the Web search engines to find information on a number of topics. Since the users may have diverse backgrounds and may have different expectations for a given query, some search engines try to personalize their results to better match the overall interests of an individual user. This task involves two great challenges. First the search engines need to be able to effectively identify the user interests and build a profile for every individual user. Second, once such a profile is available, the search engines need to rank the results in a way that matches the interests of a given user. In this article, we present our work towards a personalized Web search engine and we discuss how we addressed each of these challenges. Since users are typically not willing to provide information on their personal preferences, for the first challenge, we attempt to determine such preferences by examining the click history of each user. In particular, we leverage a topical ontology for estimating a user's topic preferences based on her past searches, i.e. previously issued queries and pages visited for those queries. We then explore the semantic similarity between the user's current query and the query-matching pages, in order to identify the user's current topic preference. For the second challenge, we have developed a ranking function that uses the learned past and current topic preferences in order to rank the search results to better match the preferences of a given user. Our experimental evaluation on the Google query-stream of human subjects over a period of 1 month shows that user preferences can be learned accurately through the use of our topical ontology and that our ranking function which takes into account the learned user preferences yields significant improvements in the quality of the search results.
Keywords: Personalized search; Web search; User preferences; Topical ontology; Topic-specific rankings
Cross-representation mediation of user models BIBAKFull-Text 35-63
  Shlomo Berkovsky; Tsvi Kuflik
Personalization is considered a powerful methodology for improving the effectiveness of information search and decision making. It has led to the dissemination of systems capable of suggesting relevant and personalized information (or items) to the users, according to their characteristics and preferences, as represented by a User Model (UM). Since the quality of the personalization largely depends on the size and accuracy of the managed UMs, it would be beneficial to enrich the UMs by mediating, i.e., importing and integrating, UMs built by other personalization systems. This work discusses and evaluates a cross-representation mediation of UMs from collaborative filtering to content-based recommender systems. According to this approach, a content-based recommender system, having partial or no UM data, can generate recommendations for users by mediating UM data of the same users, collected by a collaborative filtering system. The mediation process transforms the UMs from the collaborative filtering ratings to the content-based weighted item features. The mediation process exploits the item descriptions that are typically not used by the collaborative filtering recommender systems. An experimental evaluation conducted in the domain of movies shows that for users with small collaborative filtering UMs, i.e., users with few item ratings, the accuracy of the recommendations provided using the mediated content-based UMs is superior to that using the original collaborative filtering UMs. Moreover, it shows that the mediation can be used to improve a content-based recommender system by incrementally mediating collaborative filtering UM data (item ratings) and enriching the available content-based UMs.
Keywords: Recommender systems; User modeling; Mediation of user models; Collaborative filtering; Content-based filtering
Unsupervised strategies for shilling detection and robust collaborative filtering BIBAKFull-Text 65-97
  Bhaskar Mehta; Wolfgang Nejdl
Collaborative filtering systems are essentially social systems which base their recommendation on the judgment of a large number of people. However, like other social systems, they are also vulnerable to manipulation by malicious social elements. Lies and Propaganda may be spread by a malicious user who may have an interest in promoting an item, or downplaying the popularity of another one. By doing this systematically, with either multiple identities, or by involving more people, malicious user votes and profiles can be injected into a collaborative recommender system. This can significantly affect the robustness of a system or algorithm, as has been studied in previous work. While current detection algorithms are able to use certain characteristics of shilling profiles to detect them, they suffer from low precision, and require a large amount of training data. In this work, we provide an in-depth analysis of shilling profiles and describe new approaches to detect malicious collaborative filtering profiles. In particular, we exploit the similarity structure in shilling user profiles to separate them from normal user profiles using unsupervised dimensionality reduction. We present two detection algorithms; one based on PCA, while the other uses PLSA. Experimental results show a much improved detection precision over existing methods without the usage of additional training time required for supervised approaches. Finally, we present a novel and highly effective robust collaborative filtering algorithm which uses ideas presented in the detection algorithms using principal component analysis.
Keywords: Shilling; Collaborative filtering; Dimensionality reduction; PCA; PLSA; Robust statistics
An architecture for making recommendations to courseware authors using association rule mining and collaborative filtering BIBAKFull-Text 99-132
  Enrique García; Cristóbal Romero
Nowadays we find more and more applications for data mining techniques in e-learning and web-based adaptive educational systems. The useful information discovered can be used directly by the teacher or author of the course in order to improve instructional/learning performance. This can, however, imply a lot of work for the teacher who can greatly benefit from the help of educational recommender systems for doing this task. In this paper we propose a system oriented to find, share and suggest the most appropriate modifications to improve the effectiveness of the course. We describe an iterative methodology to develop and carry out the maintenance of web-based courses to which we have added a specific data mining step. We apply association rule mining to discover interesting information through students' usage data in the form of IF-THEN recommendation rules. We have also used a collaborative recommender system to share and score the recommendation rules obtained by teachers with similar profiles along with other experts in education. Finally, we have carried out experiments with several real groups of students using a web-based adaptive course. The results obtained demonstrate that the proposed architecture constitutes a good starting point to future investigations in order to generalize the results over many course contents.
Keywords: Association rule mining; Recommender systems; e-learning; Web-based adaptive education; Courseware design
Case-studies on exploiting explicit customer requirements in recommender systems BIBAKFull-Text 133-166
  Markus Zanker; Markus Jessenitschnig
Recommender Systems (RS) suggest useful and interesting items to users in order to increase user satisfaction and online conversion rates. They typically exploit explicit or implicit user feedback such as ratings, buying records or clickstream data and apply statistical methods to derive recommendations. This paper focuses on explicitly formulated customer requirements as the sole type of user feedback. Its contribution lies in comparing different techniques such as knowledge- and utility-based methods, collaborative filtering, association rule mining as well as hybrid variants when user models consist solely of explicit customer requirements. We examine how this type of user feedback can be exploited for personalization in e-commerce scenarios. Furthermore, examples of actual online shops are developed where such contextual user information is available, demonstrating how more efficient RS configurations can be implemented. Results indicate that, especially for new users, explicit customer requirements are a useful source of feedback for personalization and hybrid configurations of collaborative and knowledge-based techniques achieve best results.
Keywords: Hybrid recommender systems; Comparative evaluation; Electronic commerce; Cold-start recommendation problem

UMUAI 2009-08 Volume 19 Issue 3

Interaction design guidelines on critiquing-based recommender systems BIBAKFull-Text 167-206
  Li Chen; Pearl Pu
A critiquing-based recommender system acts like an artificial salesperson. It engages users in a conversational dialog where users can provide feedback in the form of critiques to the sample items that were shown to them. The feedback, in turn, enables the system to refine its understanding of the user's preferences and prediction of what the user truly wants. The system is then able to recommend products that may better stimulate the user's interest in the next interaction cycle. In this paper, we report our extensive investigation of comparing various approaches in devising critiquing opportunities designed in these recommender systems. More specifically, we have investigated two major design elements which are necessary for a critiquing-based recommender system: critiquing coverage--one vs. multiple items that are returned during each recommendation cycle to be critiqued; and critiquing aid--system-suggested critiques (i.e., a set of critique suggestions for users to select) vs. user-initiated critiquing facility (i.e., facilitating users to create critiques on their own). Through a series of three user trials, we have measured how real-users reacted to systems with varied setups of the two elements. In particular, it was found that giving users the choice of critiquing one of multiple items (as opposed to just one) has significantly positive impacts on increasing users' decision accuracy (particularly in the first recommendation cycle) and saving their objective effort (in the later critiquing cycles). As for critiquing aids, the hybrid design with both system-suggested critiques and user-initiated critiquing support exhibits the best performance in inspiring users' decision confidence and increasing their intention to return, in comparison with the uncombined exclusive approaches. Therefore, the results from our studies shed light on the design guidelines for determining the sweetspot balancing user initiative and system support in the development of an effective and user-centric critiquing-based recommender system.
Keywords: Critiquing-based recommender systems; Decision support; Preference revision; User control; Example critiquing; Dynamic critiquing; Hybrid critiquing; User evaluation; Usability; Human--computer interaction
Managing uncertainty in group recommending processes BIBAKFull-Text 207-242
  Luis M. de Campos; Juan M. Fernández-Luna
While the problem of building recommender systems has attracted considerable attention in recent years, most recommender systems are designed for recommending items to individuals. The aim of this paper is to automatically recommend a ranked list of new items to a group of users. We will investigate the value of using Bayesian networks to represent the different uncertainties involved in a group recommending process, i.e. those uncertainties related to mechanisms that govern the interactions between group members and the processes leading to the final choice or recommendation. We will also show how the most common aggregation strategies might be encoded using a Bayesian network formalism. The proposed model can be considered as a collaborative Bayesian network-based group recommender system, where group ratings are computed from the past voting patterns of other users with similar tastes.
Keywords: Group recommending; Management of uncertainty; Probabilistic Graphical Models
Addressing the assessment challenge with an online system that tutors as it assesses BIBAKFull-Text 243-266
  Mingyu Feng; Neil Heffernan
Secondary teachers across the United States are being asked to use formative assessment data (Black and Wiliam 1998a,b; Roediger and Karpicke 2006) to inform their classroom instruction. At the same time, critics of US government's No Child Left Behind legislation are calling the bill "No Child Left Untested". Among other things, critics point out that every hour spent assessing students is an hour lost from instruction. But, does it have to be? What if we better integrated assessment into classroom instruction and allowed students to learn during the test? We developed an approach that provides immediate tutoring on practice assessment items that students cannot solve on their own. Our hypothesis is that we can achieve more accurate assessment by not only using data on whether students get test items right or wrong, but by also using data on the effort required for students to solve a test item with instructional assistance. We have integrated assistance and assessment in the ASSISTment system. The system helps teachers make better use of their time by offering instruction to students while providing a more detailed evaluation of student abilities to the teachers, which is impossible under current approaches. Our approach for assessing student math proficiency is to use data that our system collects through its interactions with students to estimate their performance on an end-of-year high stakes state test. Our results show that we can do a reliably better job predicting student end-of-year exam scores by leveraging the interaction data, and the model based on only the interaction information makes better predictions than the traditional assessment model that uses only information about correctness on the test items.
Keywords: Intelligent tutoring system; ASSISTments; Dynamic assessment; Assistance metrics; Interactive tutoring
Empirically building and evaluating a probabilistic model of user affect BIBAKFull-Text 267-303
  Cristina Conati; Heather Maclaren
We present a probabilistic model of user affect designed to allow an intelligent agent to recognise multiple user emotions during the interaction with an educational computer game. Our model is based on a probabilistic framework that deals with the high level of uncertainty involved in recognizing a variety of user emotions by combining in a Dynamic Bayesian Network information on both the causes and effects of emotional reactions. The part of the framework that reasons from causes to emotions (diagnostic model) implements a theoretical model of affect, the OCC model, which accounts for how emotions are caused by one's appraisal of the current context in terms of one's goals and preferences. The advantage of using the OCC model is that it provides an affective agent with explicit information not only on which emotions a user feels but also why, thus increasing the agent's capability to effectively respond to the users' emotions. The challenge is that building the model requires having mechanisms to assess user goals and how the environment fits them, a form of plan recognition. In this paper, we illustrate how we built the predictive part of the affective model by combining general theories with empirical studies to adapt the theories to our target application domain. We then present results on the model's accuracy, showing that the model achieves good accuracy on several of the target emotions. We also discuss the model's limitations, to open the ground for the next stage of the work, i.e., complementing the model with diagnostic information.
Keywords: Affective computing; Dynamic Bayesian networks; Evaluation; User modeling

UMUAI 2009-10 Volume 19 Issue 4

Can eyes reveal interest? Implicit queries from gaze patterns BIBAKFull-Text 307-339
  Antti Ajanki; David R. Hardoon; Samuel Kaski
We study a new research problem, where an implicit information retrieval query is inferred from eye movements measured when the user is reading, and used to retrieve new documents. In the training phase, the user's interest is known, and we learn a mapping from how the user looks at a term to the role of the term in the implicit query. Assuming the mapping is universal, that is, the same for all queries in a given domain, we can use it to construct queries even for new topics for which no learning data is available. We constructed a controlled experimental setting to show that when the system has no prior information as to what the user is searching, the eye movements help significantly in the search. This is the case in a proactive search, for instance, where the system monitors the reading behaviour of the user in a new topic. In contrast, during a search or reading session where the set of inspected documents is biased towards being relevant, a stronger strategy is to search for content-wise similar documents than to use the eye movements.
Keywords: Eye movements; Implicit relevance feedback; Information retrieval; Machine learning; Support vector machines
Log file analysis for disengagement detection in e-Learning environments BIBAKFull-Text 341-385
  Mihaela Cocea; Stephan Weibelzahl
Most e-Learning systems store data about the learner's actions in log files, which give us detailed information about learner behaviour. Data mining and machine learning techniques can give meaning to these data and provide valuable information for learning improvement. One area that is of particular importance in the design of e-Learning systems is learner motivation as it is a key factor in the quality of learning and in the prevention of attrition. One aspect of motivation is engagement, a necessary condition for effective learning. Using data mining techniques for log file analysis, our research investigates the possibility of predicting users' level of engagement, with a focus on disengaged learners. As demonstrated previously across two different e-Learning systems, HTML-Tutor and iHelp, disengagement can be predicted by monitoring the learners' actions (e.g. reading pages and taking test/quizzes). In this paper we present the findings of three studies that refine this prediction approach. Results from the first study show that two additional reading speed attributes can increase the accuracy of prediction. The second study suggests that distinguishing between two different patterns of disengagement (spending a long time on a page/test and browsing quickly through pages/tests) may improve prediction in some cases. The third study demonstrates the influence of exploratory behaviour on prediction, as most users at the first login familiarize themselves with the system before starting to learn.
Keywords: e-Learning; Disengagement; Log files analysis; Educational data mining; Motivation; User modelling

UMUAI 2009-12 Volume 19 Issue 5

CTRL: A research framework for providing adaptive collaborative learning support BIBAKFull-Text 387-431
  Erin Walker; Nikol Rummel
There is evidence suggesting that providing adaptive assistance to collaborative interactions might be a good way of improving the effectiveness of collaborative activities. In this paper, we introduce the Collaborative Tutoring Research Lab (CTRL), a research-oriented framework for adaptive collaborative learning support that enables researchers to combine different types of adaptive support, particularly by using domain-specific models as input to domain-general components in order to create more complex tutoring functionality. Additionally, the framework allows researchers to implement comparison conditions by making it easier to vary single factors of the adaptive intervention. We evaluated CTRL by designing adaptive and fixed support for a peer tutoring setting, and instantiating the framework using those two collaborative scenarios and an individual tutoring scenario. As part of the implementation, we integrated pre-existing components from the Cognitive Tutor Algebra (CTA) with custom-built components. The three conditions were then compared in a controlled classroom study, and the results helped us to contribute to learning sciences research in peer tutoring. CTRL can be generalized to other collaborative scenarios, but the ease of implementation relates to the complexity of the existing components used. CTRL as a framework has yielded a full implementation of an adaptive support system and a controlled evaluation in the classroom.
Keywords: Adaptive collaborative learning support; Intelligent collaborative learning systems; Cognitive tutoring systems; Collaboration modeling; Peer tutoring; Classroom evaluation
Adaptive systems in the era of the semantic and social web, a survey BIBAKFull-Text 433-486
  Ilaria Torre
In this paper we provide a classification of adaptive systems with respect to the kind of semantic technology they exploit to accomplish or improve specific adaptation and user modeling tasks. This classification is based on a distinction between strong semantic techniques and weak semantic techniques. The former are techniques based on the Semantic Web, while the latter regard technologies that, in different ways, annotate resources, enriching their meaning. This second category includes, in particular, Web 2.0 social annotations and mixed approaches between social annotations and Semantic Web techniques. While the impact of the Semantic Web on adaptive systems has been discussed in several survey papers, the potential of weak semantic technologies has, so far, received little attention. The aim of this analysis is to fill this gap. Therefore, we will discuss contributions and limits of both approaches, but we will focus special attention on weak semantic adaptive systems.
Keywords: Semantic web; Web 2.0; Tag; Annotation; User model; Adaptation; Semantic adaptive systems; Review