Understanding The Privacy Methods, Implications, and Challenges of Educational Data Mining.
Panel Name
Cybersecurity, Privacy, and Artificial Intelligence
Location
Lecture Center Concourse
Start Date
3-5-2019 3:00 PM
End Date
3-5-2019 5:00 PM
Presentation Type
Poster Session
Abstract
Studies on educational data mining have massively advanced the analytical understanding of student learning, outcome predictions, student modeling, and better evaluation. While the information retrieved can improve educational outcomes, such studies must not break the wall of trust or compromise student privacy. To this end, it’s imperative to understand the methods of how privacy is ensured in the field of educational data mining and learning analytics, the limitations of these strategies, the complications that may follow, and the possible resolutions. In this project, we take a systematic approach to review studies in the educational data mining field. Initially, we examine common data types collected in these studies. The characteristics of that data are examined, and the potential privacy implications of it. The security/privacy-preserving methods are surveyed in said studies. Then we provide a discussion on the limitations of these privacy approaches, and identify open challenges. Finally, we discuss future avenues for further privacy research in this field. Our research will serve as a roadmap for those that are looking to understand the current data privacy concerns in the educational data mining field. Additionally, it will also help the researchers in the field understand the implications of their data collection and possible privacy protection methods.
Select Where This Work Originated From
Course assignment/project
First Faculty Advisor
Liyue Fan
First Advisor Email
liyuefan@albany.edu
First Advisor Department
Digital Forensics
The work you will be presenting can best be described as
Finished or mostly finished by conference date
Understanding The Privacy Methods, Implications, and Challenges of Educational Data Mining.
Lecture Center Concourse
Studies on educational data mining have massively advanced the analytical understanding of student learning, outcome predictions, student modeling, and better evaluation. While the information retrieved can improve educational outcomes, such studies must not break the wall of trust or compromise student privacy. To this end, it’s imperative to understand the methods of how privacy is ensured in the field of educational data mining and learning analytics, the limitations of these strategies, the complications that may follow, and the possible resolutions. In this project, we take a systematic approach to review studies in the educational data mining field. Initially, we examine common data types collected in these studies. The characteristics of that data are examined, and the potential privacy implications of it. The security/privacy-preserving methods are surveyed in said studies. Then we provide a discussion on the limitations of these privacy approaches, and identify open challenges. Finally, we discuss future avenues for further privacy research in this field. Our research will serve as a roadmap for those that are looking to understand the current data privacy concerns in the educational data mining field. Additionally, it will also help the researchers in the field understand the implications of their data collection and possible privacy protection methods.