Seed project: Investigate Machine Learning Techniques for Decision-Making Support in K-12 Educational Context
The main aim of this seed application is to investigate the use and application of Machine Learning (ML) algorithms to further the understanding of learning processes. ML, coupled with Learning Analytics (LA), can deliver analytics that allow teachers to make sense of the data and possibly support students.
Project information
Title
Investigate Machine Learning Techniques for Decision-Making Support in K-12 Educational Context
Applicants
Linnaeus University: Italo Masiello, Jonas Nordqvist, Zeynab (Artemis) Mohseni, Karl-Olof Lindahl
Project period
March-December 2023
Financier
Linnaeus University Centre for Data Intensive Sciences and Applications (DISA)
Core research areas
Computer Science, Mathmatics
Proposal
Proposal DISA seed project.pdf
Research groups
EdTechLnu
Computational Social Sciences (CSS)
Data Intensive Sciences and Applications (DISA)
Data Intensive Software Technologies and Applications (DISTA)
More about the project
Education, mostly higher education for the moment, has begun to recognize the opportunities that arise from analysing learner-produced data trails and digital data related to learners. Thus, the aim of EdTechLnu group is to create a pedagogical, legal, ethical, and information secure system, or sets of systems, with visual dashboard decision support for teachers, so that they can make pedagogical and teaching decision informed by data.
Research show that educational dashboard based on ML that specifically target primary and secondary level of education is unique with only very few research groups globally working on similar research.
However, the EdTechLnu group is lacking the competences to look at the data generated by the different datasets, to understand how they are encoded, and how they can be integrated. Therefore, speaking specifically about this application, the seed group is instead meant to collaborate on the data aspect of the research. The seed funds are going to be used by one researcher to make use of ML algorithms to try to find interrelations that can inform teachers’ insights through dashboards.
In a previous publication by Mohseni et al (2020), we have tested seven different types of ML classification algorithms (Linear, k_Nearest Neighbors, Decision tree, Neural Network, Support Vector Machines, Random Forest, and XGBoost) to learn from imbalanced datasets and discovered that Neural Network had the highest accuracy. With the seed funds, we intend to run similar pilot studies to understand the optimal application of ML algorithms.
The goals of the seed project are:
- To use a data-centric approach with various ML algorithms to empirically find patterns in student data related to learning and online behaviors.
- To use ML analyses to inform educational dashboards for teachers.
- To publish the results in at least one scientific journal.
- To write a research application for an in-depth study, first to VINNOVA, but other suitable funders will be identified.
Expected Results:
The main outcome of this seed project is expected to be a project group that will work together with the main aim of securing funding to develop a ML and LA dashboard to provide a decision support tool for teachers to assist student learning. Secondary results include one publication in a peer reviewed journal of relevance.
What is a seed project?
A seed project is a minor project funded by a knowledge environment or a research group at the university. The aim is to launch and promote excellent research. Depending on the financier, a seed project may be to idenfify new or deepen existing collaborations, preferably cross-disciplinary ones, to explore possible research issues in a feasibility study, to collect empirical material, or to write an application for external funding.
DISA's seed projects
Learn more about the seed project concept and DISA's other seed projects.