Assessments improve student learning. More than 50 years ago, Benjamin Bloom showed how to conduct this process in practical and highly effective ways when he described the practice of mastery learning (Bloom, 1968, 1971). Open-ended problems in assignments, as opposed to more closed-ended problems where there are a small set of known correct responses, offer an opportunity for students to demonstrate their understanding by articulating their underlying thought processes. In such problems, students are required to explain in a sentence or two, how to solve a particular problem or how they arrived at a solution. Open-ended responses stimulate a thought process in a student and allow teachers to better evaluate the student’s deeper understanding of a topic beyond what can be observed in other problem types. Due to the open-ended nature of student responses to these problems, however, it is sometimes difficult for teachers to devote time to assessing student work, which causes students to apply lower effort or disengage from such problems if it is believed that a teacher is unlikely to attend to it. In order to promote better student engagement with these open-ended questions and to motivate them to apply more effort in answering these questions, I have built an infrastructure to conduct RCTs(Randomized Control Trials) with open-ended problems within ASSISTments, an online assessment tool; I have built an infrastructure that caters to machine learning models for the automated assessment of the student work. I am using this infrastructure to design an RCT that will evaluate the effect of prompted self-revision on the quality of the student responses.
| Identifer | oai:union.ndltd.org:wpi.edu/oai:digitalcommons.wpi.edu:etd-theses-2384 |
| Date | 15 May 2020 |
| Creators | Vinayakumar, Meghana Kasal |
| Contributors | Neil Heffernan, Advisor |
| Publisher | Digital WPI |
| Source Sets | Worcester Polytechnic Institute |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Masters Theses (All Theses, All Years) |
Page generated in 0.0016 seconds