scholarly journals Dispositional Learning Analytics for Supporting Individualized Learning Feedback

2021 ◽  
Vol 6 ◽  
Author(s):  
Dirk Tempelaar ◽  
Bart Rienties ◽  
Quan Nguyen

An important goal of learning analytics (LA) is to improve learning by providing students with meaningful feedback. Feedback is often generated by prediction models of student success using data about students and their learning processes based on digital traces of learning activities. However, early in the learning process, when feedback is most fruitful, trace-data-based prediction models often have limited information about the initial ability of students, making it difficult to produce accurate prediction and personalized feedback to individual students. Furthermore, feedback generated from trace data without appropriate consideration of learners’ dispositions might hamper effective interventions. By providing an example of the role of learning dispositions in an LA application directed at predictive modeling in an introductory mathematics and statistics module, we make a plea for applying dispositional learning analytics (DLA) to make LA precise and actionable. DLA combines learning data with learners’ disposition data measured through for example self-report surveys. The advantage of DLA is twofold: first, to improve the accuracy of early predictions; and second, to link LA predictions with meaningful learning interventions that focus on addressing less developed learning dispositions. Dispositions in our DLA example include students’ mindsets, operationalized as entity and incremental theories of intelligence, and corresponding effort beliefs. These dispositions were inputs for a cluster analysis generating different learning profiles. These profiles were compared for other dispositions and module performance. The finding of profile differences suggests that the inclusion of disposition data and mindset data, in particular, adds predictive power to LA applications.

Author(s):  
David Santandreu Calonge ◽  
Karina M. Riggs ◽  
Mariam Aman Shah ◽  
Tim A. Cavanagh

Academic research in the past decade has indicated that using data and analyzing learning in curriculum design decisions can lead to improved student performance and student success. As learning in many instances has evolved into the flexible format online, anywhere at any time, learning analytics could potentially provide impactful insights into student engagement in massive open online courses (MOOCs). These may contribute to early identification of “at risk” participants and provide MOOC facilitators, educators, and learning designers with insights on how to provide effective interventions to ensure participants meet the course learning outcomes and encourage retention and completion of a MOOC. This chapter uses the essential human biology MOOC within the Australian AdelaideX initiative to implement learning analytics to investigate and compare demographics of participants, patterns of navigation including participation and engagement for passers and non-passers in two iterations of the MOOC, one instructor-led, and second self-paced.


Author(s):  
Bjarne Schmalbach ◽  
Markus Zenger ◽  
Michalis P. Michaelides ◽  
Karin Schermelleh-Engel ◽  
Andreas Hinz ◽  
...  

Abstract. The common factor model – by far the most widely used model for factor analysis – assumes equal item intercepts across respondents. Due to idiosyncratic ways of understanding and answering items of a questionnaire, this assumption is often violated, leading to an underestimation of model fit. Maydeu-Olivares and Coffman (2006) suggested the introduction of a random intercept into the model to address this concern. The present study applies this method to six established instruments (measuring depression, procrastination, optimism, self-esteem, core self-evaluations, and self-regulation) with ambiguous factor structures, using data from representative general population samples. In testing and comparing three alternative factor models (one-factor model, two-factor model, and one-factor model with a random intercept) and analyzing differential correlational patterns with an external criterion, we empirically demonstrate the random intercept model’s merit, and clarify the factor structure for the above-mentioned questionnaires. In sum, we recommend the random intercept model for cases in which acquiescence is suspected to affect response behavior.


2015 ◽  
Vol 31 (1) ◽  
pp. 20-30 ◽  
Author(s):  
William S. Helton ◽  
Katharina Näswall

Conscious appraisals of stress, or stress states, are an important aspect of human performance. This article presents evidence supporting the validity and measurement characteristics of a short multidimensional self-report measure of stress state, the Short Stress State Questionnaire (SSSQ; Helton, 2004 ). The SSSQ measures task engagement, distress, and worry. A confirmatory factor analysis of the SSSQ using data pooled from multiple samples suggests the SSSQ does have a three factor structure and post-task changes are not due to changes in factor structure, but to mean level changes (state changes). In addition, the SSSQ demonstrates sensitivity to task stressors in line with hypotheses. Different task conditions elicited unique patterns of stress state on the three factors of the SSSQ in line with prior predictions. The 24-item SSSQ is a valid measure of stress state which may be useful to researchers interested in conscious appraisals of task-related stress.


2018 ◽  
Author(s):  
Douglas Samuel ◽  
John D. Ranseen

Previous studies have indicated a consistent profile of basic personality traits correlated with adult Attention Deficit Hyperactivity Disorder (ADHD) (e.g., Ranseen, Campbell, & Baer, 1998; Nigg et al., 2002). In particular, research has found that low scores of the Conscientiousness trait and high scores on Neuroticism have been correlated with ADHD symptomatology. However, to date there is limited information concerning the range of effect resulting from medication treatment for adult ADHD. During an 18 month period, 60 adults were diagnosed with ADHD based on strict, DSM-IV criteria at an outpatient clinic. This evaluation included a battery of neuropsychological tests and a measure of general personality (i.e., the NEO PI-R). Eleven of these participants returned to complete the battery a second time. The pre-post comparisons revealed significant changes following sustained stimulant treatment on both the neuropsychological and self-report measures. These individuals also displayed significant changes on two domains of the NEO PI-R. They showed a significant decrease on the domain of Neuroticism, indicating that now see themselves as less prone to experience negative emotional states such as anxiety and depression. Additionally, they also reported a significant increase on their scores on the domain of conscientiousness. This increase suggests that they see themselves as more organized and dependable.


2020 ◽  
pp. 001112872098189
Author(s):  
Thomas J. Holt ◽  
Kevin F. Steinmetz

Criminological inquiry consistently identifies a gender difference in offending rates, which are also evident among certain forms of cybercrime. The gender difference in cybercrime offending is particularly large within computer hacking, though few have specifically addressed this issue through applications of criminological theory. The current study attempted to account for the gender disparity in hacking through a test of power-control theory, which considers the role of class and family structure. This analysis also incorporated an extension of power-control theory through the influence of low self-control. Using data from the Second International Self-Report of Delinquency study (ISRD-2), logistic regression analyses were estimated, producing partial support for both theories to account for hacking. Implications for theory and research were explored in detail.


Energies ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 2332
Author(s):  
Cecilia Martinez-Castillo ◽  
Gonzalo Astray ◽  
Juan Carlos Mejuto

Different prediction models (multiple linear regression, vector support machines, artificial neural networks and random forests) are applied to model the monthly global irradiation (MGI) from different input variables (latitude, longitude and altitude of meteorological station, month, average temperatures, among others) of different areas of Galicia (Spain). The models were trained, validated and queried using data from three stations, and each best model was checked in two independent stations. The results obtained confirmed that the best methodology is the ANN model which presents the lowest RMSE value in the validation and querying phases 1226 kJ/(m2∙day) and 1136 kJ/(m2∙day), respectively, and predict conveniently for independent stations, 2013 kJ/(m2∙day) and 2094 kJ/(m2∙day), respectively. Given the good results obtained, it is convenient to continue with the design of artificial neural networks applied to the analysis of monthly global irradiation.


2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 800-800
Author(s):  
Sam Li ◽  
Isaac Donkor ◽  
Liang Hong ◽  
Kevin Lu ◽  
Bei Wu

Abstract There is limited information on the impact of cognition function on dental care utilization and costs. This study used the Medicare current beneficiaries survey in 2016 and included 4,268 participants 65+. Dental care utilization and costs were measured by self-report and included preventive and treatment events. Negative binomial regression and generalized linear regression were used to examine the impact of Alzheimer’s disease (AD) and related dementia (RD) on dental care utilization and costs. We found that AD was not associated with dental care utilization, but RD was associated with a lower number of total treatment dental care visits (IRR: 0.60; 95% CI: 0.37~0.98). RD was not associated with dental care costs, but AD was associated with higher total dental care costs (estimate: 1.08; 95% CI: 0.14~2.01) and higher out-of-pocket costs (estimate: 1.25; 95% CI: 0.17~2.32). AD and RD had different impacts on different types of dental care utilization and costs. Part of a symposium sponsored by the Oral Health Interest Group.


Nutrients ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 795
Author(s):  
Mary M. Murphy ◽  
Kelly A. Higgins ◽  
Xiaoyu Bi ◽  
Leila M. Barraj

Limited information is available on protein intake and adequacy of protein intake among pregnant women. Using data from a sample of 528 pregnant women in the National Health and Nutrition Examination Surveys (NHANES) 2003–2012, usual intake of protein (g/day and g/kg body weight (bw)/day) and prevalence of intake below the Estimated Average Requirement (EAR) by trimester of pregnancy were calculated using the National Cancer Institute method. Percent contributions to protein intake by source (i.e., plant and animal, including type of animal source) were also calculated. Mean usual intake of protein was 88 ± 4.3, 82 ± 3.1, and 82 ± 2.9 g/day among women in trimester 1, 2, and 3 of pregnancy, respectively, or 1.30 ± 0.10, 1.35 ± 0.06, and 1.35 ± 0.05 g/kg bw/day, respectively. An estimated 4.5% of women in the first trimester of pregnancy consumed less protein than the EAR of 0.66 g/kg bw/day; among women in the second and third trimesters of pregnancy, 12.1% and 12.8% of women, respectively, consumed less protein than the EAR of 0.88 g/kg bw/day. Animal sources of protein accounted for approximately 66% of total protein. Findings from this study show that one in eight women in the second and third trimesters of pregnancy have inadequate intake of protein. Pregnant women should be encouraged to consume sufficient levels of protein from a variety of sources.


2021 ◽  
Author(s):  
Hossein Estiri ◽  
Zachary Strasser ◽  
Sina Rashidian ◽  
Jeffrey Klann ◽  
Kavishwar Wagholikar ◽  
...  

The growing recognition of algorithmic bias has spurred discussions about fairness in artificial intelligence (AI) / machine learning (ML) algorithms. The increasing translation of predictive models into clinical practice brings an increased risk of direct harm from algorithmic bias; however, bias remains incompletely measured in many medical AI applications. Using data from over 56 thousand Mass General Brigham (MGB) patients with confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), we evaluate unrecognized bias in four AI models developed during the early months of the pandemic in Boston, Massachusetts that predict risks of hospital admission, ICU admission, mechanical ventilation, and death after a SARS-CoV-2 infection purely based on their pre-infection longitudinal medical records. We discuss that while a model can be biased against certain protected groups (i.e., perform worse) in certain tasks, it can be at the same time biased towards another protected group (i.e., perform better). As such, current bias evaluation studies may lack a full depiction of the variable effects of a model on its subpopulations. If the goal is to make a change in a positive way, the underlying roots of bias need to be fully explored in medical AI. Only a holistic evaluation, a diligent search for unrecognized bias, can provide enough information for an unbiased judgment of AI bias that can invigorate follow-up investigations on identifying the underlying roots of bias and ultimately make a change.


Sign in / Sign up

Export Citation Format

Share Document