Our paper was accepted to IEEE CogMI 2019.
With Computer Science (CS) class sizes that are often large, it is challenging to provide effective personalized feedback to students. Intelligent Tutoring Companions can provide such feedback and improve CS students’ experience. This work describes the construction of a Tutoring Companion, Annete, designed to support students in a university Java programming course by providing them with intelligent feedback generated by a neural network. Annete is embedded into the Eclipse Integrated Development Environment (IDE), which is an environment that is already familiar to students in programming courses. Embedding Annete into Eclipse improves her effectiveness, as the students do not need to learn how to use an additional tool. While the student works in Eclipse, Annete collects 21 pieces of data from the student’s code, including whether certain key words are used, error messages from the compiler, and cyclomatic complexity. When a run attempt, debug attempt, or a request for help occurs in Eclipse, Annete uses the data available to infer a feedback message to show to the student. Our approach is evaluated among 28 CS students completing a programming assignment while Annete assists them. Results suggest that students feel supported while working with Annete and show potential for using neural network modeling with embedded tutoring companions in the future. Challenges are discussed, as well as opportunities for future work.
Day M., Penumala, M. R., and Gonzalez-Sanchez J. (2019). Annete: An Intelligent Tutoring Companion Embedded into the Eclipse IDE. Proceeding of the IEEE First International Conference on Cognitive Machine Intelligence (CogMI). Pp. 71-80. IEEE. doi.org/10.1109/CogMI48466.2019.00018