Rozestraten, Karlijn (2021) Identifying Underlying Skills in Math Problems - A Data-Driven Approach. Master's Thesis / Essay, Human-Machine Communication.
|
Text
mCCS_2021_RozestratenKM.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (95kB) |
Abstract
Over the years, various intelligent, personalised, data-driven and cognitive tutoring systems have been developed to aid in teaching and tracking of study progress of students. These systems can make use of a cognitive model that is designed for a task that a student is expected to learn. Cognitive models require predetermined skills that are usually based on what the model designer assumes are needed. To better future development, this project aimed to develop an unsupervised machine learning algorithm that can determine underlying skills required for math problems from the accuracy scores of exam data. The developed knowledge graph algorithm calculates a partial ordering on a set questions in a data set with multiple mathematical topics. The algorithm determines relations between pairs of questions that later forms a hierarchy of the questions. A relation represents that a question at a higher level in the hierarchy contained a subset of skills that is required for a question at the lower level. The algorithm is validated on a simulated data set and then applied to existing mathematical exam data sets. The algorithm was found not be designed to determine the required skills for solving the math problems from the data. The results of this project bring us a step closer to accomplishing an objective determination of skills required in math problem-solving tests. Nonetheless, more research is required to identify exact skills required for solving math problems from exam data.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Taatgen, N.A. |
| Degree programme: | Human-Machine Communication |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 27 Jan 2022 09:47 |
| Last Modified: | 27 Jan 2022 09:47 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/26505 |
Actions (login required)
 |
View Item |