Mechanical TA 2: Peer Grading With TA and Algorithmic SupportGlobal
Mechanical TA 2 (MTA2) is an open-source, distributed peer grading system that boosts performance by leveraging both trusted TAs and computationally intensive algorithms. The system provides a unified platform for submission of assignments, grading by both peers and TAs, and reporting of feedback. It also supports dividing students into different pools based on their peer-grading prowess; mechanisms for automated calibration and spot checking; and the ability for students to appeal grades and to give feedback about individual reviews. Bayesian inference and mixed-integer programming algorithms perform interpretable aggregation of peer grades and estimate students’ grading performance, providing feedback, incentivizing high-quality grading, and directing TA spot checks appropriately. Analysis of data from four offerings of a large undergraduate class provides empirical evidence of MTA2’s effectiveness.
Thu 21 MarDisplayed time zone: Pacific Time (US & Canada) change
10:45 - 12:00 | Assessment & GradingPapers at Meeting Rooms B110-112 Chair(s): Amanpreet Kapoor University of Florida, USA | ||
10:45 25mTalk | Diverging assessments: What, Why, and ExperiencesGlobal Papers Amin Sakzad Monash University, David Paul University of New England, Judy Sheard Monash University, Ljiljana Brankovic University of New England, Matthew P. Skerritt RMIT University, Nan Li University of Wollongong, Australia, Sepehr Minagar Monash University, Simon , William Billingsley University of New England DOI | ||
11:10 25mTalk | Mechanical TA 2: Peer Grading With TA and Algorithmic SupportGlobal Papers DOI | ||
11:35 25mTalk | Rubric for the Quality of Answers to Student Queries about CodeGlobal Papers Svana Esche Technical University of Darmstadt DOI | ||