Learning at scale often requires domain-specific automation such as assessment and feedback. An organization locked in to a general learning platform without these specialist automations limits its pedagogical offering. An ecosystem of interoperable, platform-agnostic microservices for domain-specific automation would solve this problem. To develop an effective ecosystem, a standard interface (API) for education microservices is required.

Effective feedback is often timely and consistent but, with large cohorts, this is not always achievable. This study explored the potential of GPT4 to generate feedback on code readability for students enrolled in a CS1 Java course. We developed rubrics based on three readability criteria: naming, commenting, and formatting. We defined feedback criteria and incorporated them into GPT4 prompts to guide feedback generation. Results were mixed: while some feedback messages closely aligned with the rubrics, offering valuable insights, others fell short in providing corrective guidance. This highlights the potential and limitations of using LLMs to generate feedback on code readability. Future research could refine these methods to improve feedback consistency and quality.

We present Menagerie, an open-ended project-scale second-semester CS1 Java assignment dataset that ran over four academic years (18/19 - 21/22). It comprises 667 submissions, with 273 being subsequently graded post hoc. The assignment was open-ended, with the students being asked to implement a 'predator/prey' simulator and to meet specific criteria, which included adding five species, competing for the same food source and keeping track of the time of day. The submissions were assessed as part of a separate study on the correctness of the solution, how well the code was designed, how readable the code is, and the quality of the documentation.

Research into automated grading has increased as Computer Science courses grow. Dynamic and static approaches are typically used to implement these graders, the most common implementation being unit testing to grade correctness. This paper expands upon an ongoing systematic literature review to provide an in-depth analysis of how machine learning (ML) has been used to grade and give feedback on programming assignments. We conducted a backward snowball search using the ML papers from an ongoing systematic review and selected 27 papers that met our inclusion criteria. After selecting our papers, we analysed the skills graded, the preprocessing steps, the ML implementation, and the models' evaluations.

Over the last few years, Computer Science class sizes have increased, resulting in a higher grading workload. To manage this workload, universities often use multiple graders to deliver the grades and associated feedback quickly. While using multiple graders enables the required turnaround times to be achieved, it does come at the cost of consistency and feedback quality. Automating the process of grading and feedback could help solve these issues. This project will look into methods to fully or partially automate grading and feedback, such as machine learning and natural language processing, to improve grade uniformity and feedback quality.