Problem-based learning supported by semantic techniques

Problem-based learning has been applied over the last three decades to a diverse range of learning environments. In this educational approach, different problems are posed to the learners so that they can develop different solutions while learning about the problem domain. When applied to conceptual modelling, and particularly to Qualitative Reasoning, the solutions to problems are models that represent the behaviour of a dynamic system. The learner's task then is to bridge the gap between their initial model, as their first attempt to represent the system, and the target models that provide solutions to that problem. We propose the use of semantic technologies and resources to help in bridging that gap by providing links to terminology and formal definitions, and matching techniques to allow learners to benefit from existing models.     

Summary Intervals for Model-Based Classification Accuracy and Consistency Indices

When scores are used to make decisions about respondents, it is of interest to estimate classification accuracy (CA), the probability of making a correct decision, and classification consistency (CC), the probability of making the same decision across two parallel administrations of the measure. Model-based estimates of CA and CC computed from the linear factor model have been recently proposed, but parameter uncertainty of the CA and CC indices has not been investigated. This article demonstrates how to estimate percentile bootstrap confidence intervals and Bayesian credible intervals for CA and CC indices, which have the added benefit of incorporating the sampling variability of the parameters of the linear factor model to summary intervals. Results from a small simulation study suggest that percentile bootstrap confidence intervals have appropriate confidence interval coverage, although displaying a small negative bias. However, Bayesian credible intervals with diffused priors have poor interval coverage, but their coverage improves once empirical, weakly informative priors are used. The procedures are illustrated by estimating CA and CC indices from a measure used to identify individuals low on mindfulness for a hypothetical intervention, and R code is provided to facilitate the implementation of the procedures.     

A model for predicting the educational use of information and communication technologies

This study of 550 persons, predominately education professionals, was designed to test an integrated theoretical model (the 4-E Model) for predicting the likelihood of the use of telecommunications-related technological innovations (in particular, e-mail, the WWW, and videoconferencing) in learning-related settings. The four Es in the model, derived from a series of previous studies (Collis & Pals, 1999), are environmental factors, effectiveness, ease of use, and (personal) engagement. The model was first tested using factor-analytic procedures on the results of a 54-item questionnaire adminstered via the WWW to a sample of 550 persons from 39 countries. Twelve factors with eigenvalues greater than 1.00 were extracted and latent variables were generated to correspond with the factors. The factors as interpreted by items with loadings <0.500 supported the 4-E Model, but indicated that the four theoretical e dimensions could be further expressed in terms of subaspects. In addition, a series of variables related to likelihood of use of e-mail, the WWW, and videoconferencing in educational settings was also subjected to a factor analysis, resulting in three latent variables representing the dependent variables for a causal model. The causal model linking the latent variables was tested using a series of LISREL analyses, one for each of the derived dependent variables. The results, which again supported the 4-E Model, showed a strong contribution of the environment subfactor relating to the organization, as well as the engagement subfactor relating to the individual's self-confidence with respect to technology use to the prediction of implementation success. Based on the results of the factor analysis and the model validation, six of the latent variables related to the 4-E Model were identified as key to implementation prediction. These variables were used in a series of analyses of key subgroups in the sample, relating to educational sector, educational role, to gender, and to age, in order to examine key discriminating variables. The results are discussed in terms of their theoretical and practical implications, including the development of a WWW-based instrument.     

How do the existing fairness metrics and unfairness mitigation algorithms contribute to ethical learning analytics?

With the widespread use of learning analytics (LA), ethical concerns about fairness have been raised. Research shows that LA models may be biased against students of certain demographic subgroups. Although fairness has gained significant attention in the broader machine learning (ML) community in the last decade, it is only recently that attention has been paid to fairness in LA. Furthermore, the decision on which unfairness mitigation algorithm or metric to use in a particular context remains largely unknown. On this premise, we performed a comparative evaluation of some selected unfairness mitigation algorithms regarded in the fair ML community to have shown promising results. Using a 3-year program dropout data from an Australian university, we comparatively evaluated how the unfairness mitigation algorithms contribute to ethical LA by testing for some hypotheses across fairness and performance metrics. Interestingly, our results show how data bias does not always necessarily result in predictive bias. Perhaps not surprisingly, our test for fairness-utility tradeoff shows how ensuring fairness does not always lead to drop in utility. Indeed, our results show that ensuring fairness might lead to enhanced utility under specific circumstances. Our findings may to some extent, guide fairness algorithm and metric selection for a given context.

Practitioner notes

What is already known about this topic

• LA is increasingly being used to leverage actionable insights about students and drive student success.
• LA models have been found to make discriminatory decisions against certain student demographic subgroups—therefore, raising ethical concerns.
• Fairness in education is nascent. Only a few works have examined fairness in LA and consequently followed up with ensuring fair LA models.

What this paper adds

• A juxtaposition of unfairness mitigation algorithms across the entire LA pipeline showing how they compare and how each of them contributes to fair LA.
• Ensuring ethical LA does not always lead to a dip in performance. Sometimes, it actually improves performance as well.
• Fairness in LA has only focused on some form of outcome equality, however equality of outcome may be possible only when the playing field is levelled.

Implications for practice and/or policy

• Based on desired notion of fairness and which segment of the LA pipeline is accessible, a fairness-minded decision maker may be able to decide which algorithm to use in order to achieve their ethical goals.
• LA practitioners can carefully aim for more ethical LA models without trading significant utility by selecting algorithms that find the right balance between the two objectives.
• Fairness enhancing technologies should be cautiously used as guides—not final decision makers. Human domain experts must be kept in the loop to handle the dynamics of transcending fair LA beyond equality to equitable LA.

     

Stories of Policing: The Role of Storytelling in Police Students’ Sensemaking of Early Work-Based Experiences

Storytelling has been shown to play a key role in transferring work experience from more experienced towards novices in a number of vocational educational practices, however previous studies have not to the same extent dealt with the role of students’ own storytelling practices for sensemaking of work experience. This study set out to examine police students’ storytelling of their first occupational experiences from a sensemaking perspective, with an analysis drawing on the concepts of enactment, selection, and retention. The study is based on participant observations of field training follow up sessions’ in the context of police education. Findings indicated that student storytelling of work experience tended to be geared towards action, extremeness and the telling of ‘war stories’. Furthermore, these type of stories functioned to enable student identification, self-enhancement and emotion management. These findings contribute to our current understanding of how students engage in sensemaking of work-based experiences and in extension how knowledge integration and learning from work placements can be structured pedagogically.     

Graph-based data mining: A new tool for the analysis and comparison of scientific domains represented as scientograms

The creation of some kind of representations depicting the current state of Science (or scientograms) is an established and beaten track for many years now. However, if we are concerned with the automatic comparison, analysis and understanding of a set of scientograms, showing for instance the evolution of a scientific domain or a face-to-face comparison of several countries, the task is titanically complex as the amount of data to analyze becomes huge and complex. In this paper, we aim to show that graph-based data mining tools are useful to deal with scientogram analysis. Subdue, the first algorithm proposed in the graph mining area, has been chosen for this purpose. This algorithm has been customized to deal with three different scientogram analysis tasks regarding the evolution of a scientific domain over time, the extraction of the common research categories substructures in the world, and the comparison of scientific domains between different countries. The outcomes obtained in the developed experiments have clearly demonstrated the potential of graph mining tools in scientogram analysis.     

The direct and indirect effects of word reading and vocabulary on adolescents’ reading comprehension: Comparing struggling and adequate comprehenders

The current study examined statistically significant differences between struggling and adequate readers using a multicomponent model of reading comprehension in 796 sixth through eighth graders, with a primary focus on word reading and vocabulary. Path analyses and Wald tests were used to investigate the direct and indirect relations of word identification, vocabulary, silent reading efficiency, and inference-making on reading comprehension. Comparing struggling versus adequate comprehenders revealed statistically significant differences in path coefficients. In both groups, vocabulary had the largest total effect when considering its direct and indirect effects. Word identification was the strongest direct predictor for struggling comprehenders (β = .18 for struggling vs. β = ? .03 for adequate), while vocabulary was the strongest predictor for adequate comprehenders (β = .40 for adequate vs. β = .14 for struggling). Findings reinforce (a) vocabulary knowledge plays a primary role in explaining individual differences in adolescent reading comprehension, (b) the need to differentiate intervention to address underlying difficulties of struggling readers, and (c) the relations of reading component skills (e.g., word reading and silent reading efficiency) to reading comprehension may be different based on reader proficiency.     

Associations of total sedentary time,screen time and non-screen sedentary time with adiposity and physical fitness in youth: the mediating effect of physical activity

The aims of the present study were: i) to examine the associations of total accelerometer-based sedentary time (ST) and specific-domain self-reported ST (i.e., screen-based, educational-based, social-based, and other-based ST) with adiposity and physical fitness in youth; and ii) to analyse the mediation effect of physical activity (PA) on associations.

This study was conducted with 415 children (9.1 ± 0.4 years) and 853 adolescents (13.6 ± 1.6 years) in Spain during 2011–2012. Total ST and PA were assessed by accelerometry. Leisure-time spent in twelve sedentary behaviours was self-reported. Adiposity and physical fitness was measured following the ALPHA battery for youth.

Total accelerometer-based ST was positively associated with global adiposity score in children, and negatively associated with global physical fitness score in children and adolescents; but relationships were not independent of PA. PA mediated all associations of accelerometer-based and self-reported ST with adiposity or physical fitness in children. Conversely, screen-, educational-, social-, and other-based ST were negatively related to physical fitness in adolescents, independently of PA.

These findings give an impetus to developing effective strategies for specifically promoting PA in children and for increasing PA while reducing ST in adolescents in order to produce improvements on adiposity and physical fitness.