3125. On Recommender Methods in E-Learning
Invited abstract in session TD-34: Advancements of OR-analytics in statistics, machine learning and data science 5, stream Advancements of OR-analytics in statistics, machine learning and data science.
Tuesday, 14:30-16:00Room: Michael Sadler LG10
Authors (first author is the speaker)
| 1. | Alejandro Fuster-Lopez
|
| Universidad de Malaga | |
| 2. | Jesús Martínez Cruz
|
| Universidad de Málaga | |
| 3. | Pablo Guerrero-García
|
| Universidad de Málaga | |
| 4. | Eligius M.T. Hendrix
|
| Computer Architecture, Universidad de Málaga |
Abstract
The use of e-learning systems has a long tradition. Students can study online helped by a system. In this context, the use of recommender systems is relatively new. In a research project, we investigated various ways to create a recommender system based on several methodologies. They all aim at facilitating the learning and understanding of a student. Methods may aim to predict, which next question or which new material (video, description) may help the student further in obtaining insight measured as getting the next question well answered. Given past information of users in a database, machine learning methods like Random Forest have been suggested and implemented. However, these are data and energy hungry types of methods. Instead, we implemented methods on collaborative filtering which is based on matrix factorization methodologies. Our investigation goes in the direction of comparing the machine learning ideas with matrix factorization ones measuring effectiveness and efficiency.
Keywords
- Analytics and Data Science
- Education and Distance Learning
Status: accepted
Back to the list of papers