Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Clustering MOOC Programming Solutions to Diversify Their Presentation to Students

Elizaveta Artser, Anastasiia Birillo, Yaroslav Golubev, Maria Tigina, Hieke Keuning, Nikolay Vyahhi, Timofey Bryksin

TL;DR

This work adapted the existing plagiarism detection tool JPlag to Python submissions on Hyperskill, a popular MOOC platform, and developed its own tool called Rhubarb, which selects one example from each of the largest clusters, thus ensuring their diversity.

Abstract

In many MOOCs, whenever a student completes a programming task, they can see previous solutions of other students to find potentially different ways of solving the problem and to learn new coding constructs. However, a lot of MOOCs simply show the most recent solutions, disregarding their diversity or quality, and thus hindering the students' opportunity to learn. In this work, we explore this novel problem for the first time. To solve it, we adapted the existing plagiarism detection tool JPlag to Python submissions on Hyperskill, a popular MOOC platform. However, due to the tool's inner algorithm, JPLag fully processed only 46 out of 867 studied tasks. Therefore, we developed our own tool called Rhubarb. This tool first standardizes solutions that are algorithmically the same, then calculates the structure-aware edit distance between them, and then applies clustering. Finally, it selects one example from each of the largest clusters, thus ensuring their diversity. Rhubarb was able to handle all 867 tasks successfully. We compared different approaches on a set of 59 real-life tasks that both tools could process. Eight experts rated the selected solutions based on diversity, code quality, and usefulness. The default platform approach of simply selecting recent submissions received on average 3.12 out of 5, JPlag - 3.77, Rhubarb - 3.50. To ensure both quality and coverage, we created a system that combines both tools. We conclude our work by discussing the future of this new problem and the research needed to solve it better.

Clustering MOOC Programming Solutions to Diversify Their Presentation to Students

TL;DR

This work adapted the existing plagiarism detection tool JPlag to Python submissions on Hyperskill, a popular MOOC platform, and developed its own tool called Rhubarb, which selects one example from each of the largest clusters, thus ensuring their diversity.

Abstract

In many MOOCs, whenever a student completes a programming task, they can see previous solutions of other students to find potentially different ways of solving the problem and to learn new coding constructs. However, a lot of MOOCs simply show the most recent solutions, disregarding their diversity or quality, and thus hindering the students' opportunity to learn. In this work, we explore this novel problem for the first time. To solve it, we adapted the existing plagiarism detection tool JPlag to Python submissions on Hyperskill, a popular MOOC platform. However, due to the tool's inner algorithm, JPLag fully processed only 46 out of 867 studied tasks. Therefore, we developed our own tool called Rhubarb. This tool first standardizes solutions that are algorithmically the same, then calculates the structure-aware edit distance between them, and then applies clustering. Finally, it selects one example from each of the largest clusters, thus ensuring their diversity. Rhubarb was able to handle all 867 tasks successfully. We compared different approaches on a set of 59 real-life tasks that both tools could process. Eight experts rated the selected solutions based on diversity, code quality, and usefulness. The default platform approach of simply selecting recent submissions received on average 3.12 out of 5, JPlag - 3.77, Rhubarb - 3.50. To ensure both quality and coverage, we created a system that combines both tools. We conclude our work by discussing the future of this new problem and the research needed to solve it better.
Paper Structure (16 sections, 4 figures, 2 tables)

This paper contains 16 sections, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Motivating Example
  3. Background
  4. JPlag
  5. Rhubarb
  6. Standardization of Submissions
  7. Measuring Distance
  8. Hierarchical Agglomerative Clustering
  9. Selecting Representative Solutions
  10. Limitations
  11. Evaluation
  12. Dataset
  13. Fine-tuning Parameters
  14. Comparison
  15. Discussion
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Examples of different students' approaches to solving the same task. Solutions (a) and (b) are algorithmically the same, while solution (c) is not, but still very similar to them. On the other hand, solutions (d) and (e) are rather different.
  • Figure 2: The general overview of Rhubarb.
  • Figure 3: The standard form of solutions (a) and (b) from Figure \ref{['fig:examples']}.
  • Figure 4: The graph with distances between the standardized solutions and clusters for solutions from Figure \ref{['fig:examples']}.