Search

In spite of their effectiveness, learning environments often fail to engage users and end up under-used. Many studies show that gamification of learning environments can enhance learners' motivation to use learning environments. However, learners react differently to specific game mechanics and little is known about how to adapt gaming features to learners' profiles. In this paper, we propose a process for adapting gaming features based on a player model. This model is inspired from existing player typologies and types of gamification elements. Our approach is implemented in a learning environment with five different gaming features, and evaluated with 266 participants. The main results of this study show that, amongst the most engaged learners (i.e., learners who use the environment the longest), those with adapted gaming features spend significantly more time in the learning environment. Furthermore, learners with features that are not adapted have a higher level of amotivation. These results support the relevance of adapting gaming features to enhance learners' engagement, and provide cues on means to implement adaptation mechanisms.

AbstractDetermining the number of latent dimensions (LD) of a data set is a ubiquitous problem, for which numerous methods have been developed. We compare some of the most effective ones on synthetic data, which allows proper evaluation given that the true number of LD is known. Results show that their performance is sensitive to data set attributes such as sparsity, number of observations in relation to number of features, and underlying feature distributions. Results also show this sensitivity is different across methods. This observation brings us to devise an ensemble technique to combine LD estimates from multiple methods and achieve an estimate that is more reliable than any single method. We also demonstrate that the variance of the estimates across the single methods is a good indicator of the expected loss of the ensemble-based LD estimate. This observation leads, in turn, to deriving a method for the assessment of the reliability of the estimate. Finally, we discuss the practical implications of the findings. [ABSTRACT FROM AUTHOR]

Learnersourcing is the process by which students submit content that enriches the bank of learning materials available to their peers, all as an authentic part of their learning experience. One example of learnersourcing is Technology-Mediated Peer Instruction (TMPI), whereby students are prompted to submit explanations to justify their choice in a multiple-choice question (MCQ), and are subsequently presented with explanations written by their peers, after which they can reconsider their own answer. TMPI allows students to contrast their reasoning with a variety of peer-submitted explanations. It is intended to foster reflection, ultimately leading to better learning. However, not all content submitted by students is adequate and it must be curated, a process that can require a significant effort by the teacher. The curation process ought to be automated for learnersourcing in TMPI to scale up to large classes, such as MOOCs. Even for smaller settings, automation is critical for the timely curation of student-submitted content, such as within a single assignment, or during a semester. We adapt methods from argument mining and natural language processing to address the curation challenge and assess the quality of student answers submitted in TMPI, as judged by their peers. The curation task is confined to the prediction of argument convincingness: an explanation submitted by a learner is considered of good quality, if it is convincing to their peers. We define a methodology to measure convincingness scores using three methods, Bradley-Terry, Crowd-Bradley-Terry and WinRate. We assess the performance of feature-rich supervised learning algorithms as well as transformer-based neural approach to predict convincingness using these scores. Experiments are conducted over different domains, from ethics to STEM. While the neural approach shows the greatest correlation between its prediction and the different convincingness measures, results show that success on this task is highly dependent on the domain and the type of question. [ABSTRACT FROM AUTHOR]

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.jss.2005.10.014 Byline: Tamer Rafla, Pierre N. Robillard, Michel Desmarais Keywords: Software architecture; Usability; Scenarios; Web applications; SAAM Abstract: Usability has primarily been served by separating the user interface from the remainder of the application. However, several researchers have recently determined that there is a direct relationship between architectural decisions and usability requirements. This leads us to conclude that more attention should be devoted to usability-driven architectural analysis methods. We present a case study, which involves adapting an existing software architecture analysis method (SAAM) for the purpose of deriving the interdependencies between architectural characteristics and usability requirements. More specifically, we investigate the impact on the architecture of implementing usability requirement changes. Potential design solutions that accommodate the corresponding usability mechanisms into the Web software architecture are presented, along with the rationale for applying them and the process by which they are obtained. We conclude by recommending how usability issues can be dealt with proactively during the design of the architecture, and explain the need to integrate those usability requirements into a software engineering process. Author Affiliation: Software Engineering Research Lab, Ecole Polytechnique de Montreal, P.O. Box 6079, Station Centre-Ville, Montreal, QC, Canada H3C 3A7 Article History: Received 14 February 2005; Revised 19 October 2005; Accepted 23 October 2005

This paper describes an algorithmic means for inducing implication networks from empirical data samples. The induced network enables efficient inferences about the values of network nodes if certain observations are made. This implication induction method is approximate in nature as probablistic network requirements are relaxed in the construction of dependence relationships based on statistical testing. In order to examine the effectiveness and validity of the induction method, several Monte-Carlo simulations were conducted, where theoretical Bayesian networks were used to generate empirical data samples - some of which were used to induce implication relations, whereas others were used to verify the results of evidential reasoning with the induced networks. The values in the implication networks were predicted by applying a modified version of the Dempster-Shafer belief updating scheme. The results of predictions were, furthermore, compared to the ones generated by Pearl's stochastic simulation method [21], a probabilistic reasoning method that operates directly on the theoretical Bayesian networks. The comparisons consistently show that the results of predictions based on the induced networks would be comparable to those generated by Pearl's method, when reasoning in a variety of uncertain knowledge domains - those that were simulated using the presumed theoretical probabilistic networks of different topologies. Moreover, our validation experiments also reveal that the comparable performance of the implication-network-based-reasoning method can be achieved with much less computational cost than Pearl's stochastic simulation method; specifically, in all our experiments, the ratio between the actual CPU time required by our method and that by Pearl's is approximately 1:100. Index Terms - Belief-network induction, probabilistic reasoning, learning algorithms, evidential reasoning, implication networks, implication-network induction, knowledge engineering, Monte-Carlo simulation, empirical validation.

This paper is concerned with the problem of measuring the uncertainty in a broad class of belief networks, as encountered in evidential reasoning applications. In our discussion, we give an explicit account of the networks concerned, and coin them the Dempster-Shafer (D-S) belief networks. We examine the essence and the requirement of such an uncertainty measure based on well-defined discrete event dynamical systems concepts. Furthermore, we extend the notion of entropy for the D-S belief networks in order to obtain an improved optimal dynamical observer. The significance and generality of the proposed dynamical observer of measuring uncertainty for the D-S belief networks lie in that it can serve as a performance estimator as well as a feedback for improving both the efficiency and the quality of the D-S belief network-based evidential inferencing. We demonstrate, with Monte Carlo simulation, the implementation and the effectiveness of the proposed dynamical observer in solving the problem of evidential inferencing with optimal evidence node selection. Index Terms--Belief networks, uncertainty modeling and management, discrete event dynamical systems, optimal evidential inferencing, controller, observer, entropy, user profile assessment.

This paper evaluates the effect on the predictive accuracy of different models of two recently proposed imputation methods, namely missForest (MF) and Multiple Imputation based on Expectation-Maximization (MIEM), along with two other imputation methods: Sequential Hot-deck and Multiple Imputation based on Logistic Regression (MILR). Their effect is assessed over the classification accuracy of four different models, namely Tree Augmented Naive Bayes (TAN) which has received little attention, Naive Bayes (NB), Logistic Regression (LR), and Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel. Experiments are conducted over fourteen binary datasets with large feature sets, and across a wide range of missing data rates (between 5 and 50%). The results from 10 fold cross-validations show that the performance of the imputation methods varies substantially between different classifiers and at different rates of missing values. The MIEM method is shown to generally give the best results for all the classifiers across all rates of missing data. While NB model does not benefit much from imputation compared to a no imputation baseline, LR and TAN are highly susceptible to gain from the imputation methods at higher rates of missing values. The results also show that MF works best with TAN, and Hot-deck degrades the predictive performance of SVM and NB models at high rates of missing values (over 30%). Detailed analysis of the imputation methods over the different datasets is reported. Implications of these findings on the choice of an imputation method are discussed. [ABSTRACT FROM AUTHOR]

Copyright of STICEF is the property of Sciences et Techniques de l'Information et de la Communication pour l'Education et la Formation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The Bayesian framework offers a number of techniques for inferring an individual's knowledge state from evidence of mastery of concepts or skills. A typical application where such a technique can be useful is Computer Adaptive Testing (CAT). A Bayesian modeling scheme, POKS, is proposed and compared to the traditional Item Response Theory (IRT), which has been the prevalent CAT approach for the last three decades. POKS is based on the theory of knowledge spaces and constructs item-to-item graph structures without hidden nodes. It aims to offer an effective knowledge assessment method with an efficient algorithm for learning the graph structure from data. We review the different Bayesian approaches to modeling student ability assessment and discuss how POKS relates to them. The performance of POKS is compared to the IRT two parameter logistic model. Experimental results over a 34 item Unix test and a 160 item French language test show that both approaches can classify examinees as master or non-master effectively and efficiently, with relatively comparable performance. However, more significant differences are found in favor of POKS for a second task that consists in predicting individual question item outcome. Implications of these results for adaptive testing and student modeling are discussed, as well as the limitations and advantages of POKS, namely the issue of integrating concepts into its structure. [ABSTRACT FROM AUTHOR]

Addresses the problem of measuring the uncertainty in a broad class of belief networks encountered in evidential reasoning applications. Dempster-Shafer belief networks; Monte-Carlo simulation studies; Entropy-based evidential inferences contrasted with those of random evidential inferences; Optimal system control for examination of uncertainty measure.

In this article, we describe a Web-based approach that defines training needs for object-oriented developers by identifying the strong and the weak areas of their knowledge. Our system is based on the use of two tools, Guide d'Auto-Apprentissage, Self-Learning Guide (GAA) and User Knowledge Assessment Technology (UKAT) developed at the Computer Research Institute of Montreal. UKAT uses a state-of-the-art user knowledge assessment method to create a user profile of the proficiency in a subject domain. GAA is a Web-based training system that uses the UKAT to personalize a training course to facilitate self-learning. As an exemplar, we are using a Java development environment. © 1999 John Wiley & Sons, Inc. Comput Appl Eng Educ 7: 162–170, 1999 [ABSTRACT FROM AUTHOR]

An introduction is presented in which the editor discusses articles in the issue on topics including adaptive hypermedia; Technology-Enhanced Learning; and self-esteem.