University of Pittsburgh

Use of big data in personalized education (Joint ISP/iSchool talk)

Assistant Professor
Friday, December 5, 2014 - 12:30pm - 1:30pm

Abstract: The volume and granularity of data produced by current educational technologies in K-16 presents an exciting opportunity to gain insights into student knowledge and how it is acquired. In this talk I will show how probabilistic graphical models of student learning, with roots in cognitive theory, have served as an effective platform to study learning phenomenon in digital learning environments. Probabilistic graphical models allow for a blend of machine learning and domain expertise and are well suited to capture the temporal aspects of student data. The models were used to improve the accuracy of student knowledge assessment and performance prediction by taking into account individual inferred prior knowledge and learning attributes of the student as well as attributes of the content. This approach proved effective in the 2010 KDD Cup competition on educational data mining when pitted against an ensemble of state-of-the-art machine learning approaches. I will also show how these same models have been posed to measure the pedagogical efficacy of problem orderings, individual resources in a MOOC, and remediation decisions made by the learning environment. The work presented was conducted using data from the Cognitive Tutors for Algebra and Geometry, the ASSISTments Platform, and recently,  Massive OpenOnline Courses (MOOC) on the edX platform. Implications for adaptivity, affective state integration, and privacy in the big data age will be discussed.


Bio: Zach Pardos is an Assistant Professor at UC Berkeley in a joint position between the School of Information and Graduate School of Education. His focal areas of study are educational data mining and learning analytics concentrating on measurement of learning in digital environments. He earned his PhD in Computer Science at Worcester Polytechnic Institute in the Tutor Research Group in 2012. Funded by a National Science Foundation Fellowship (GK-12) he spent extensive time on the front lines of K-12 education working with teachers and students to integrate educational technology into the curriculum as a formative assessment tool. He was program co-chair of the 2014 conference on Educational Data Mining, on the organizing committee for the 2014 Learning Analytics and Knowledge conference, and serves on the executive committee for the Artificial Intelligence in Education Society. He has received numerous academic awards and honors for extensions of his thesis work on ?Predictive Models of Learning? including a top prize applying his educational analytics in the 2010 KDD Cup, an international big data competition on predicting student performance within an intelligent tutoring system. Pardos comes to UC Berkeley after a post-doc at MIT studying Massive Open Online Courses. He is on the Vice Provost?s committee for education data distribution and privacy policy at UC Berkeley and directs the Computational Approaches to Human Learning (CAHL) research lab.

Copyright 2009 | Web site by UMC Web Team