Prospective PhD Students

We are hosting an event for prospective graduate students to visit Worcester Polytechnic Institute on Saturday, November 10! Here is my welcome message! Register Here! Come learn about Learning Sciences & Technologies, Computer Science, and Data Science

Come visit WPI, me, and others!

I support PhD students in three areas: Computer Science, Data Science, and Learning Sciences & Technologies. The requirements are different for each program.

For example, one of my students in the LS&T program, Korinn Ostrow, graduated in May 2018 and essentially received a PhD in psychology but with a technology focus. She completed 6+ peer-reviewed publications of randomized controlled trials (RCTs) of different interventions. She also has at least 7 papers in which she analyzed the large data sets in ASSISTments, an online learning platform that I created, which is offered as a free public service of WPI. 

I have PhD students in CS who have gone on to work at the University of California, Berkeley. I have other students who built components of ASSISTments and then tested them.  

When reviewing PhD student applications, I look for students who have at least one of following: 
1) a strong background in cognitive science, 
2) a strong math background (probability, statistics, machine learning, data mining), and 
3) research experience and published work. 

I support students focused on 1) educational data mining and 2) software engineering that will be used to create tools that can be used to run randomized controlled trials on student learning, as well as folks who have some teaching experience.  

Two students of mine who combine the first two criteria are Seth A. Adjei and Xiaolu Xiong who each built their own systems (PLACEments and ARRS respectively) within ASSISTments. Both have lots of skills that allow them to: 1) do predictive analytics (educational data mining; for example, how does the data from this feature help us better predict state test scores or student knowledge?) and 2) run randomized controlled trials. For PLACEments we have many RCTs going to answer research questions of the following nature: 1) is a particular feature good? and 2) can we figure out what arcs in a prerequisite graph are good and useful in and of themselves? A feature is defined as "good" when it works, improves student learning, and teachers see value in it. We also factor in its popularity when determining if it is good. Check out ARRS results here.
I also have three full-time middle school math teachers who are pursuing their PhDs in LS&T. What I look for in such students is totally different as they are not going to write code. You can visit Kim Kelly's website for an example. 

Prospective students should read my recent papers and look at my recent activities (workshop presentations, etc.) to determine if our interests are a good match.

I respond to email inquiries only if our mutual interests seem strong and the student has the qualifications listed above. When emailing me, please cc my assistant Tricia Desmarais. (Her email is td [at]