Educational Data Mining in the Service of Building Detectors of Loosing interest

Speaker Bio:

Neil Heffernan (https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fsites.google.com%2Fsite%2Fneilheffernanscv%2Fhome&data=01%7C01%7Cshirin.mojarad%40mheducation.com%7Ceaf34136c9d84ab8c1ca08d51fc7557c%7Cf919b1efc0c347358fca0928ec39d8d5%7C0&sdata=450dwF3FOahoa%2BXPH662O5DSr7tdZo3BCCChMe0b9VY%3D&reserved=0) is a professor of Computer Science and the co-director of the PhD program in Learning Sciences and Technologies. He developed ASSISTments not only to help teachers be more effective in the classroom but also so that he could use the platform to conduct studies to improve the quality of education. He is very passionate about educational data mining. Professor Heffernan enjoys supervising WPI students helping them create ASSISTments content and features. Several student projects have resulted in peer-reviewed publications looking at comparing different ways to optimize student learning. Professor Heffernan's goal is to give ASSISTments to millions across the US and internationally as a free service of WPI.

The talk:

"During the session, I will talk about educational data mining and building better educational technology products. I created ASSISTments at WPI, a product used by 50,000 last year to solve 12 million problems. I started ASSISTments about a decade ago, and ever sense then we have been logging student performance. In this session, I will talk about a cool use of that data. The 2017 ASSISTments Data Mining Competition is sponsored by the Big Data for Education Spoke of the Northeast Big Data Hub, an NSF initiative to help spur progress in educational research using big data. Competing individuals/teams are using educational data from ASSISTments, tool for middle school mathematics, to make long term predictions regarding STEM career entry from 7th grade click stream data. Why do we need this? School are already using 'drop out' detectors for early warning system, but they also need early warning systems for 'these students are losing interest in STEM' detectors. ' The results of this competition could help inform the design of systems that could help try to reignite student's interest in studying STEM. Successful entries will be invited to submit both to a conference workshop (at EDM2018, in Buffalo, NY) and to a special issue of the Journal of Educational Data Mining. Currently, more than 40 researchers have added their predictions to the competition board - apply your own cross-validated prediction models using your preferred data mining techniques and join in our pursuit to better understand the predictive powers of early STEM engagement. For more information, please visit https://sites.google.com/view/assistmentsdatamining/data-mining-competition-2017 (https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fsites.google.com%2Fview%2Fassistmentsdatamining%2Fdata-mining-competition-2017&data=01%7C01%7Cshirin.mojarad%40mheducation.com%7Ceaf34136c9d84ab8c1ca08d51fc7557c%7Cf919b1efc0c347358fca0928ec39d8d5%7C0&sdata=SrvXB4P%2BIZLld8JR9dXkZM6YxjU46UqAjQIOA%2FHivAk%3D&reserved=0). I will talk about the competition and similar works we have done."

Schedule:

6.00PM - 6.30PM: Networking, dinner and drinks

6.30PM - 7.30PM: Talk by Prof. Neil Haffernan

7.30PM - 8.00PM: Networking and drinks