Summer 2015 Research Projects
Below you will find a list of faculty that will be conducting research during the Summer of 2015 and are looking for research students.
Project: Personalizing Education (Anna Rafferty)
Interactive educational technologies, including many educational websites, have become more and more popular, both for students to use in their free time and in the classroom. These technologies engage and motivate students, and they offer opportunities to customize instruction and feedback for each individual student. For example, imagine a computer program that can look at the steps you took to solve a problem and infer why you got the problem incorrect. The program can then suggest that you watch a particular video, targeted at helping you relearn the relevant concept, or perhaps have you try a few more problems to gather more information about what you understand and what you misunderstand. In my research, I focus on building algorithms that can make inferences about understanding based on the data collected in educational technologies. These algorithms typically involve machine learning as well as models of human learning. Once I have an algorithm that can make these inferences, I explore how accurate the inferences are and how we can use the inferences to make personalized decisions about feedback and instructions.
In the research we'll be working on this summer, we'll mainly focus on inferring students' mastery of algebra skills. This research is part of a larger project aimed at building a free online algebra tutor. The basic website has been built, we've developed an algorithm for inferring understanding, and some algebra problem solving data has been collected. This means there's enough here to help you get started quickly and lots of places to take things further! Some things we'll likely explore include:
1) Extending the types of problems covered by the algebra tutor
2) Testing the properties of the inference algorithm: when do its interpretations differ from human interpretations? How can we fix these interpretations? How can we automatically determine the space of possible algebra misunderstandings based on looking at a large set of human problem solving data?
3) Running behavioral experiments to test the effectiveness of customized feedback
The exact focus of your work will depend on how things evolve over the course of the spring and summer and your own interests and background. This project combines cognitive science, machine learning, and statistics, so it's a great opportunity to see the multidisciplinary nature of computer science! Depending on your interests, there may also be opportunities to explore educational data other than algebra, but the bulk of the work will be related to algebra.
I plan on hiring ~2 positions for the summer. This position will be for 10 weeks of research.
CS 201 or its equivalent is appropriate preparation for this project. Experience with any of probability, statistics, psychology, AI/data or mining would be a definite plus, but is not required. Ideally, you would do a small independent study with me in the spring to start reading relevant background material.
Project: Git for People Who Actually Want to Learn Git (Dave Musicant)
The version control system Git has become very popular for developers to track and share the code that they write. Accordingly, Git has been making its way into classrooms in computer science programs around the world. One of the main challenges that students face in using Git is its complexity. Git is really powerful, but it contains a lot of complicated functionality that students don't need to use right away. Moreover, understanding at a deeper level how Git works can be quite useful, and current Git clients don't necessarily help users understand this. Finally, instructors use Git in the classroom, and typically need to accomplish a variety of tedious and complex details to organize projects and submissions.
The goal of this project is to design and build a new Git client for use by students to help them use Git successfully with a minimum of challenges, likely by use of a subset of Git commands, but also to help them understand at a deeper level how Git works. Furthermore, the client would support the different major Git workflows that exist in different classes. This project won't be finished by the end of this summer, but students who participate will be able to have a pivotal role in initial design and getting the project started. Opportunities to continue working on the project in the fall might be possible.
Students who are accepted for this project (hopefully two of them, depending on available funding) will work for 5 weeks during the summer of 2015. Additionally, students should be available to participate in an independent study during the spring of 2015 to read papers, examine existing tools (both Git-related and otherwise), and have discussions to begin planning the project.
CS 201 or its equivalent is a minimal prerequisite for the project. Experience with software design as well as version control systems would be definite plus, but is not required.
Finally: the department will also be hiring Carleton students to work as research assistants for the Summer Computer Science Institute (SCSI), which is a summer program at Carleton for high school students. Applications for that position will be announced at a later date. When applying for this project, feel free to mention if you might also be interested in working as a research assistant for that program. It would likely be possible to work 5 weeks this summer on the Git project, and an additional 3 weeks as a research assistant for SCSI.