277 research outputs found
ahaim5357/10.17605-osf.io-zcbjx: ASSISTments: XPRIZE Digital Learning Challenge
No full textRelease of the dataset and code used to analyze the data collected for Toward Improving Effectiveness of Crowdsourced, On-Demand Assistance From Authors in Online Learning Platforms. This is a project for the ASSISTments X team submitted to the XPRIZE Digital Learning Challenge.
Citation
@misc{Haim_Cheng_Prihar_Heffernan_Heffernan_2022,
title={Toward Improving Effectiveness of Crowdsourced, On-Demand Assistance From Authors in Online Learning Platforms},
url={osf.io/zcbjx},
DOI={10.17605/OSF.IO/ZCBJX},
publisher={OSF},
author={Haim, Aaron and Cheng, Li and Prihar, Ethan and Heffernan, Neil T, III and Heffernan, Cristina},
year={2022},
month={Aug}
}We would like to thank the NSF (e.g., 2118725, 2118904, 1950683, 1917808, 1931523, 1940236, 1917713, 1903304, 1822830, 1759229, 1724889, 1636782, & 1535428), IES (e.g., R305N210049, R305D210031, R305A170137, R305A170243, R305A180401, & R305A120125), GAANN (e.g., P200A180088 & P200A150306), EIR (U411B190024 & S411B210024), ONR (N00014-18-1-2768), and Schmidt Futures. None of the opinions expressed here are that of the funders. We are funded under an NHI grant (R44GM146483) with Teachly as a SBIR
Theoretical Components of Workplace Safety Climate and Their Implications for Practice
No full textManagement safety commitment is an important theoretical factor in safety climate measurement and research; however, the influence of co-workers has received less attention. This study investigated whether co-worker safety attitudes and behaviours contributed explanatory variance to associations with burnout or whether management attitudes and behaviours primarily determine this association. Hospitality employees (N = 111) completed safety climate, psychosocial safety climate (PSC), and burnout measures. Results showed safety climate was significantly correlated with personal, work and customer-related burnout. Multiple regressions showed co-worker factors did not add predictive capacity for burnout above management factors, although did for determining whether workers experienced customer-related burnout. Results were compared to findings for Disability Support Workers where co-worker factors added predictive capacity above management factors for burnout. Findings suggested worker and manager safety-related attitudes and behaviours are important theoretical components of safety climate, but their relative influence varies according to the safety climate measure used and organisational structure.Cassandra Heffernan, Julia Harries and Neil Kirb
How to Open Science: A Reproducibility Author Survey of the Artificial Intelligence in Education Conference
No full textA peer review with author input analyzing the open science principles and reproducibility of full papers, short papers, and posters sent to the 22nd and 23rd Artificial Intelligence in Education conference
Recommended from our members
An Empirical Evaluation of Student Learning by the Use of a Computer Adaptive System
No full textNumerous methods to assess student knowledge are present throughout every step of a studentsÂ’ education. Skill-based assessments include homework, quizzes and tests while curriculum exams comprise of the SAT and GRE. The latter assessments provide an indication as to how well a student has retained a learned national curriculum however they are unable to identify how well a student performs at a fine grain skill level. The former assessments hone in on a specific skill or set of skills, however, they require an excessive amount of time to collect curriculum-wide data. We've developed a system that assesses students at a fine grain level in order to identify non- mastered skills within each studentÂ’s zone of proximal development.
“PLACEments” is a graph-driven computer adaptive test which not only provides thorough student feedback to educators but also delivers a personalized remediation plan to each student based on his or her identified non-mastered skills. As opposed to predicting state test scores, PLACEments objective is to personalize learning for students and encourage teachers to employ formative assessment techniques in the classroom. We have conducted a randomized controlled study to evaluate the learning value PLACEments provides in comparison to traditional methods of targeted skill mastery and retention
How To Open Science: A Principle Author Survey and Reproducibility Development of the Educational Data Mining Conference
No full textA peer review with author input analyzing the open science principles and developing reproducibility metrics of full papers, short papers, and posters sent to the 14th and 15th Educational Data Mining conference
How To Open Science: A Principle and Reproducibility Author Survey of the Artificial Intelligence in Education Conference
No full textA peer review with author input analyzing the open science principles and reproducibility of full papers, short papers, and posters sent to the 22nd and 23rd Artificial Intelligence in Education conference
How To Open Science: A Principle Author Survey, Reproducibility Development, and Statement Compliance Analysis of the Learning @ Scale Conference
No full textA peer review with author input analyzing the open science principles, developing reproducibility metrics, and reviewing the open science statement compliance of full papers, short papers, and posters sent to the 8th and 9th Learning @ Scale conference
Recommended from our members
Identifying Struggling Students by Comparing Online Tutor Clickstreams
No full textNew ways to identify students in need of assistance are imperative to the evolution of online tutoring platforms. Currently implemented models to identify struggling students use costly and tedious classroom observation paired with student's platform usage, and are often suitable for only a subset of students. With the recent influx of new students to online tutoring platforms due to COVID-19, a simple method to quickly identify struggling students could help facilitate effective remote learning. To this end, we created an anomaly detection algorithm that models the normal behavior of students during remote learning and recognizes when students deviate from this behavior. We demonstrated how anomalous behavior not only revealed which students needed additional assistance, but also helped predict student learning outcomes and reduced the confidence intervals in research experiments performed within the online tutoring platform
Recommended from our members
Improving Automated Assessment for Student Open-responses in Mathematics
No full textOpen-ended questions in mathematics are commonly used by teachers to monitor and assess students’ deeper conceptual understanding of content. Student answers to these types of questions often exhibit a combination of language, drawn diagrams and tables, and mathematical formulas and expressions that supply teachers with insight into the processes and strategies adopted by students in formulating their responses. While these student responses help to inform teachers about their students’ progress and understanding, the amount of variation in these responses can make it difficult and time-consuming for teachers to manually read, assess, and provide feedback on student work. For this reason, there has been a growing body of research in developing AI-powered tools to support teachers in this task. This work seeks to build upon the prior work that presents a model designed to help automate the assessment of student responses to open-ended questions in mathematics through sentence-level semantic representations. We conduct an error analysis of this model, to examine characteristics of student responses that may be considered to further improve the method. We find that this model performs poorly in presence of mathematical terms and images in student responses. We then introduce a model as a step toward the improvement of this method in presence of mathematical terms and we find that this new model outperforms the previously published benchmarks across three different metrics
33 Experiments : Precise unbiased estimation in randomized experiments using auxiliary observational data
No full textThis Data Set includes data from two places. The first 22 experiments from "Selent, D., Patikorn, T., & Heffernan, N. (2016, April). Assistments dataset from multiple randomized controlled experiments. In Proceedings of the Third (2016) ACM Conference on Learning@ Scale (pp. 181-184). "
The Second data set has not been published before and refer to them as Study 2 in the paper and as "The 11 additional experiments". We also include extensive log data. There two data sets were brought together for a paper: "Gagnon-Bartsch, J. A., A. C. Sales*, J. A., Wu, E., Botelho, A. F., Erickson, J. A., Miratrix, L. W. & Heffernan, N. T. (Accepted 2023) Precise unbiased estimation in randomized experiments using auxiliary observational data. Journal of Casual Inference.
- …
