Measuring the impact of an educational intervention continues to be the interest of teachers, researchers, and educational institutions around the world. This type of evaluation makes it possible to identify the teaching practices, materials, and educational programs that most benefit the students' learning process, also providing evidence for decision-making. In the case of higher education, impact measurement faces at least two major challenges. The first challenge is how to organize, store, and analyze vast and complex volumes of students’ information. The second challenge is how to improve the quality of decision-making to generate a positive effect inside and outside of educational institutions. A methodological alternative to solve these challenges is educational data mining (EDM). Educational data mining is an emerging discipline that arises from integrating three larger areas: computer science, statistics, and education. In particular, recent educational literature has reported the successful use of various data mining techniques such as visualization, classification, and clustering for the analysis of educational data. For all the above, this panel will make a critical review of the advantages, limitations, and prospects of using educational data mining for impact measurement in higher education.
Event Recording:
At the end of the event, the Call for Proposals "Bringing New Solutions to the Challenges of Predicting and Countering Student Dropout in Higher Education" will be introduced.
Address
Registration for the event has finished. Thank you for your participation.