Improving Feedback from Automated Reviews of Student Spreadsheets

Abstract

Spreadsheets are one of the most widely used tools for end users. As a result, spreadsheets such as Excel are now included in many curricula. However, digital solutions for assessing spreadsheet assignments are still scarce in the teaching context. Therefore, we have developed an Intelligent Tutoring System (ITS) to review students' Excel submissions and provide individualized feedback automatically. Although the lecturer only needs to provide one reference solution, the students' submissions are analyzed automatically in several ways: value matching, detailed analysis of the formulas, and quality assessment of the solution. To take the students' learning level into account, we have developed feedback levels for an ITS that provide gradually more information about the error by using one of the different analyses. Feedback at a higher level has been shown to lead to a higher percentage of correct submissions and was also perceived as well understandable and helpful by the students.