PREDICTING MANIPULATION ATTEMPTS BY STUDENTS ON LEARNING MANAGEMENT SYSTEMS: AN APPROACH USING MACHINE LEARNING MODEL

Date

2023-12-18

Author

Görmezoğlu, Mehmet Melih

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

84
views

33
downloads

Cite This

This study focuses on the identification of students' behavior, spanning from 1st grade to 8th grade, within a designated Learning Management System, specifically aiming to detect potential instances of attempting to "game the system." The analysis employs a two-step approach: firstly, utilizing K-means clustering to reveal patterns in students' behavior based on the log data from the Learning Management System, and subsequently applying the XGBoost classification method to predict whether a student is engaged in attempts to manipulate the system. The selection of relevant features is informed by domain knowledge, providing an insight of the key indicators. The study concludes by offering improvement suggestions for Learning Management Systems, aimed at enhancing predictive outcomes of “gaming the system” behaviors and fostering a more robust educational environment to mitigate such behaviors.

Subject Keywords

Data Mining, Data Science, Clustering Method, Classification Method, Gaming the System

URI

https://hdl.handle.net/11511/107657

Collections

Graduate School of Informatics, Thesis