HCI Bibliography Home | HCI Journals | About UMUAI | Journal Info | UMUAI Journal Volumes | Detailed Records | RefWorks | EndNote | Hide Abstracts
UMUAI Tables of Contents: 1112131415161718192021222324

User Modeling and User-Adapted Interaction 21

Editors:Alfred Kobsa
Standard No:ISSN 0924-1868 (print) EISSN 1573-1391 (online)
Links:link.springer.com | Table of Contents
  1. UMUAI 2011-04 Volume 21 Issue 1/2
  2. UMUAI 2011-08 Volume 21 Issue 3
  3. UMUAI 2011-10 Volume 21 Issue 4/5

UMUAI 2011-04 Volume 21 Issue 1/2

Special Issue on Data Mining for Personalized Educational Systems

Preface to the special issue on data mining for personalised educational systems BIBFull-Text 1-3
  Cristóbal Romero; Sebastián Ventura
A personalized learning content adaptation mechanism to meet diverse user needs in mobile learning environments BIBAKFull-Text 5-49
  Jun-Ming Su; Shian-Shyong Tseng; Huan-Yu Lin
With the heterogeneous proliferation of mobile devices, the delivery of learning materials on such devices becomes subject to more and more requirements. Personalized learning content adaptation, therefore, becomes increasingly important to meet the diverse needs imposed by devices, users, usage contexts, and infrastructure. Historical server logs offer a wealth of information on hardware capabilities, learners' preferences, and network conditions, which can be utilized to respond to a new user request with the personalized learning content created from a previous similar request. In this paper, we propose a Personalized Learning Content Adaptation Mechanism (PLCAM), which applies data mining techniques, including clustering and decision tree approaches, to efficiently manage a large number of historical learners' requests. The proposed method will intelligently and directly deliver proper personalized learning content with higher fidelity from the Sharable Content Object Reference Model (SCORM)-compliant Learning Object Repository (LOR) by means of the proposed adaptation decision and content synthesis processes. Furthermore, the experimental results indicate that it is efficient and is expected to prove beneficial to learners.
Keywords: Personalized learning content; Content adaptation; Mobile learning environment; Data mining; Learning object repository
Activity sequence modelling and dynamic clustering for personalized e-learning BIBAKFull-Text 51-97
  Mirjam Köck; Alexandros Paramythis
Monitoring and interpreting sequential learner activities has the potential to improve adaptivity and personalization within educational environments. We present an approach based on the modeling of learners' problem solving activity sequences, and on the use of the models in targeted, and ultimately automated clustering, resulting in the discovery of new, semantically meaningful information about the learners. The approach is applicable at different levels: to detect pre-defined, well-established problem solving styles, to identify problem solving styles by analyzing learner behaviour along known learning dimensions, and to semi-automatically discover learning dimensions and concrete problem solving patterns. This article describes the approach itself, demonstrates the feasibility of applying it on real-world data, and discusses aspects of the approach that can be adjusted for different learning contexts. Finally, we address the incorporation of the proposed approach in the adaptation cycle, from data acquisition to adaptive system interventions in the interaction process.
Keywords: Adaptivity; User modeling; E-learning; Data mining; Clustering; Unsupervised learning
An analysis of students' gaming behaviors in an intelligent tutoring system: predictors and impacts BIBAKFull-Text 99-135
  Kasia Muldner; Winslow Burleson
Students who exploit properties of an instructional system to make progress while avoiding learning are said to be "gaming" the system. In order to investigate what causes gaming and how it impacts students, we analyzed log data from two Intelligent Tutoring Systems (ITS). The primary analyses focused on six college physics classes using the Andes ITS for homework and test preparation, starting with the research question: What is a better predictor of gaming, problem or student? To address this question, we developed a computational gaming detector for automatically labeling the Andes data, and applied several data mining techniques, including machine learning of Bayesian network parameters. Contrary to some prior findings, the analyses indicated that student was a better predictor of gaming than problem. This result was surprising, so we tested and confirmed it with log data from a second ITS (the Algebra Cognitive Tutor) and population (high school students). Given that student was more predictive of gaming than problem, subsequent analyses focused on how students gamed and in turn benefited (or not) from instructional features of the environment, as well as how gaming in general influenced problem solving and learning outcomes.
Keywords: Educational data mining; Gaming; Utility of hints; Bayesian network parameter learning
Empirically evaluating the application of reinforcement learning to the induction of effective and adaptive pedagogical strategies BIBAKFull-Text 137-180
  Min Chi; Kurt VanLehn; Diane Litman
For many forms of e-learning environments, the system's behavior can be viewed as a sequential decision process wherein, at each discrete step, the system is responsible for selecting the next action to take. Pedagogical strategies are policies to decide the next system action when there are multiple ones available. In this project we present a Reinforcement Learning (RL) approach for inducing effective pedagogical strategies and empirical evaluations of the induced strategies. This paper addresses the technical challenges in applying RL to Cordillera, a Natural Language Tutoring System teaching students introductory college physics. The algorithm chosen for this project is a model-based RL approach, Policy Iteration, and the training corpus for the RL approach is an exploratory corpus, which was collected by letting the system make random decisions when interacting with real students. Overall, our results show that by using a rather small training corpus, the RL-induced strategies indeed measurably improved the effectiveness of Cordillera in that the RL-induced policies improved students' learning gains significantly.
Keywords: Reinforcement learning; Pedagogical strategy; Machine learning; Human learning
Content-free collaborative learning modeling using data mining BIBAKFull-Text 181-216
  Antonio R. Anaya; Jesús G. Boticario
Modeling user behavior (user modeling) via data mining faces a critical unresolved issue: how to build a collaboration model based on frequent analysis of students in order to ascertain whether collaboration has taken place. Numerous human-based and knowledge-based solutions to this problem have been proposed, but they are time-consuming or domain-dependent. The diversity of these solutions and their lack of common characteristics are an indication of how unresolved this issue remains. Bearing this in mind, our research has made progress on several fronts. First, we have found supportive evidence, based on a collaborative learning experience with hundreds of students over three consecutive years, that an approach using domain independent learning that is transferable to current e-learning platforms helps both students and teachers to manage student collaboration better. Second, the approach draws on a domain-independent modeling method of collaborative learning based on data mining that helps clarify which user-modeling issues are to be considered. We propose two data mining methods that were found to be useful for evaluating student collaboration, and discuss their respective advantages and disadvantages. Three data sources to generate and evaluate the collaboration model were identified. Third, the features being modeled were made accessible to students in several meta-cognitive tools. Their usage of these tools showed that the best approach to encourage student collaboration is to show only the most relevant inferred information, simply displayed. Moreover, these tools also provide teachers with valuable modeling information to improve their management of the collaboration. Fourth, an ontology, domain independent features and a process that can be applied to current e-learning platforms make the approach transferable and reusable. Fifth, several open research issues of particular interest were identified. We intend to address these open issues through research in the near future.
Keywords: Collaborative learning; Collaboration modeling; Data mining; Open models; Collaboration evaluation; Meta-cognitive tools in collaborative learning
A data mining approach to guide students through the enrollment process based on academic performance BIBAKFull-Text 217-248
  César Vialardi; Jorge Chue; Juan Pablo Peche
Student academic performance at universities is crucial for education management systems. Many actions and decisions are made based on it, specifically the enrollment process. During enrollment, students have to decide which courses to sign up for. This research presents the rationale behind the design of a recommender system to support the enrollment process using the students' academic performance record. To build this system, the CRISP-DM methodology was applied to data from students of the Computer Science Department at University of Lima, Perú. One of the main contributions of this work is the use of two synthetic attributes to improve the relevance of the recommendations made. The first attribute estimates the inherent difficulty of a given course. The second attribute, named potential, is a measure of the competence of a student for a given course based on the grades obtained in related courses. Data was mined using C4.5, KNN (K-nearest neighbor), Naïve Bayes, Bagging and Boosting, and a set of experiments was developed in order to determine the best algorithm for this application domain. Results indicate that Bagging is the best method regarding predictive accuracy. Based on these results, the "Student Performance Recommender System" (SPRS) was developed, including a learning engine. SPRS was tested with a sample group of 39 students during the enrollment process. Results showed that the system had a very good performance under real-life conditions.
Keywords: Data mining; Enrollment process; Supervised classification; Machine learning; Recommender systems; Predictive accuracy

UMUAI 2011-08 Volume 21 Issue 3

Evaluating and improving adaptive educational systems with learning curves BIBAKFull-Text 249-283
  Brent Martin; Antonija Mitrovic
Personalised environments such as adaptive educational systems can be evaluated and compared using performance curves. Such summative studies are useful for determining whether or not new modifications enhance or degrade performance. Performance curves also have the potential to be utilised in formative studies that can shape adaptive model design at a much finer level of granularity. We describe the use of learning curves for evaluating personalised educational systems and outline some of the potential pitfalls and how they may be overcome. We then describe three studies in which we demonstrate how learning curves can be used to drive changes in the user model. First, we show how using learning curves for subsets of the domain model can yield insight into the appropriateness of the model's structure. In the second study we use this method to experiment with model granularity. Finally, we use learning curves to analyse a large volume of user data to explore the feasibility of using them as a reliable method for fine-tuning a system's model. The results of these experiments demonstrate the successful use of performance curves in formative studies of adaptive educational systems.
Keywords: Empirical evaluation; Intelligent tutoring systems; Student modeling; User modelling; Domain modelling; Learning curves
User model interoperability: a survey BIBAKFull-Text 285-331
  Francesca Carmagnola; Federica Cena
Nowadays a large number of user-adaptive systems has been developed. Commonly, the effort to build user models is repeated across applications and domains, due to the lack of interoperability and synchronization among user-adaptive systems. There is a strong need for the next generation of user models to be interoperable, i.e. to be able to exchange user model portions and to use the information that has been exchanged to enrich the user experience. This paper presents an overview of the well-established literature dealing with user model interoperability, discussing the most representative work which has provided valuable solutions to face interoperability issues. Based on a detailed decomposition and a deep analysis of the selected work, we have isolated a set of dimensions characterizing the user model interoperability process along which the work has been classified. Starting from this analysis, the paper presents some open issues and possible future deployments in the area.
Keywords: User model interoperability; User modeling; Interoperability; User-adaptive systems

UMUAI 2011-10 Volume 21 Issue 4/5

Special Issue on Personalization for e-Health: In memory of Fiorella de Rosis and Alison Cawsey

Preface to the special issue on personalization for e-health BIBFull-Text 333-340
  Floriana Grasso; Cécile Paris
Motivating reflection about health within the family: the use of goal setting and tailored feedback BIBAKFull-Text 341-376
  Nathalie Colineau; Cécile Paris
It is widely acknowledged that obesity is a serious health issue. Despite governments' campaigns and initiatives to raise the level of awareness, the proportion of adults classified as overweight or obese is increasing steadily. As a result, there has been a growing interest in Human Computer Interaction and User Modelling to study how to support health behaviour change. While most of the work to date has focused on individuals, medical research has shown that family engagement plays an important role on health behaviour. To consider the family context, we are developing technology that facilitates health discussions and encourages supportive behaviour within the family. We investigate how to motivate members of a family to reflect upon their lifestyle and think of ways in which they can make it healthier. In particular, we have looked at whether providing explicit goals and tailored feedback can have an impact. During a two week trial with families in which we explored these strategies, we found that setting a collective goal for the family influenced how much the family as a whole contributed, and that feedback increased significantly mothers' participation. Our results also suggest that establishing a family goal encouraged families to work together and, in particular, to help each other find ways to be healthier. Finally, 76% of participants reported discussing the task with someone in their family, and, also discussing it together as a family (57%).
Keywords: Motivation strategies; Goal setting theory; Lifestyle and wellbeing; Family support; Health behaviour; Evaluation
Towards personalized decision support in the dementia domain based on clinical practice guidelines BIBAKFull-Text 377-406
  Helena Lindgren
A set of evidence-based clinical practice guidelines has been synthesized and integrated in the clinical decision support system DMSS-R (Dementia Management and Support System) to support clinical routines and reasoning processes as performed by individual health professionals in daily practice. DMSS-R provides advice, tailored to individual and often exceptional patient cases, to the user while providing guidance to the next step in the assessments and support for hypothesis generation and evaluation throughout the process. This paper describes DMSS-R and the results of a case study in clinical practice where the system was used. The case study included interviews and observations of the clinical investigation process as undertaken in 41 real patient cases with suspected dementia. Two physicians participated, one of whom was considered a novice regarding dementia while the other had a moderate level of skills. Initially, both physicians were unfamiliar with DMSS-R. A group of nurses together with care personnel and relatives were also involved. The most important contribution of DMSS-R at the point of care, apart from the tailored explanatory support related to a patient case, was the educational support it provided. This was partly manifested in a change of routines in the encounter with patients. Aspects regarding the individual health care professional's need for a personalized support system are discussed and put in relation to the team's need for support, and in relation to the diversity of disease manifestations in this group of patients, which reinforces patient-centric assessments.
Keywords: Clinical decision-support systems; Dementia; Activity theory; Continuing medical education; Clinical practice guidelines; Clinical practice; Interaction design; Activity-centered design; Evaluation; Case study
Personalized emergency medical assistance for disabled people BIBAKFull-Text 407-440
  Luca Chittaro; Elio Carchietti; Luca De Marco
Being able to promptly and accurately choose a proper course of action in the field is a crucial aspect of emergency response. For this reason, emergency medical services (EMS) rely on well established procedures that apply to the most frequent cases first responders encounter in their practice, but do not include special cases concerning (sensory, motor or cognitive) disabled persons. In these cases, first responders may end up applying suboptimal or possibly wrong procedures or lose precious time trying to adapt on-the-fly to the special case. This paper proposes both (i) a detailed patient model for EMS that can account for peculiar aspects of the many existing disabilities and (ii) an adaptive information system called PRESYDIUM (Personalized Emergency System for Disabled Humans) that provides tailored instructions in the field for helping medical first responders in dealing with disabled persons. More precisely, we will illustrate and discuss: (i) the design and development process of PRESYDIUM, (ii) the patient model, which is partly based on the ICF (International Classification of Functioning, Disability and Health) standard proposed by the World Health Organization, (iii) the knowledge base used by the system to provide tailored instructions to medical first responders, (iv) the Web-based architecture of the system, (v) the different interfaces--including one for mobile devices--the system provides to enable all the identified stakeholders (disabled persons, their families, clinicians, EMS call center operators, medical first responders) to easily access and possibly provide data to the system, (vi) the evaluation of the validity of the patient model and of the system usability which has been conducted with end users.
Keywords: Personalized e-health information systems; Patient models; Disabled patients; First responders; Emergency medical services; Tailored instructions; Tailored decision support; Knowledge-based systems; Web-based systems; Mobile applications
A user modeling approach for reasoning about interaction sensitive to bother and its application to hospital decision scenarios BIBAKFull-Text 441-484
  Robin Cohen; Hyunggu Jung; Michael W. Fleming
In this paper, we present a framework for interacting with users that is sensitive to the cost of bother and then focus on its application to decision making in hospital emergency room scenarios. We begin with a model designed for reasoning about interaction in a single-agent single-user setting and then expand to the environment of multiagent systems. In this setting, agents consider both whether to ask other agents to perform decision making and at the same time whether to ask questions of these agents. With this fundamental research as a backdrop, we project the framework into the application of reasoning about which medical experts to interact with, sensitive to possible bother, during hospital decision scenarios, in order to deliver the best care for the patients that arrive. Due to the real-time nature of the application and the knowledge-intensive nature of the decisions, we propose new parameters to include in the reasoning about interaction and sketch their usefulness through a series of examples. We then include a set of experimental results confirming the value of our proposed approach for reasoning about interaction in hospital settings, through simulations of patient care in those environments. We conclude by pointing to future research to continue to extend the model for reasoning about interaction in multiagent environments for the setting of time-critical care in hospital settings.
Keywords: Reasoning about interaction; Modeling bother; Multiagent systems; Hospital decision making; Coordination of teams of health professionals; Choosing medical experts
Design and implementation of a web-based Tailored Gymnasium to enhance self-management of Fibromyalgia BIBAKFull-Text 485-511
  Luca Camerini; Michele Giacobazzi
The aim of this article is to describe the design and development of an online gymnasium that proposes personalized exercise videos to users affected by fibromyalgia. Fibromyalgia syndrome is a chronic condition characterized by widespread pain in muscles, ligaments and tendons, usually associated with sleep disorders and fatigue. Physical exercise is considered as an important component of non-pharmacological treatments of this pathology, and the internet is praised as a powerful resource to promote and improve physical exercise. Yet, while online personalization of health interventions to consumers must be grounded on empirically based guidelines, guidelines for fibromyalgia-targeted exercises are scant. The achievements presented in this paper are twofold. Firstly, we illustrate how we reached definition of the relevant factors for tailoring exercise videos in relation to fibromyalgia. Secondly, we explain the general framework of the application that is composed of an interview module (that investigates the determinant values of a specific user), an adaptation module (presenting the tailored set of exercises) and a logging component (used to monitor users' interactions with the website). The paper concludes with a discussion on the strengths and weaknesses of the proposed approach.
Keywords: Personalized online information system; Tailoring health communication; Health technology; Fibromyalgia; Self-management