Search

Automated feedback generation for introductory programming assignments is useful for programming education. Most works try to generate feedback to correct a student program by comparing its behavior with an instructor’s reference program on selected tests. In this work, our aim is to generate verifiably correct program repairs as student feedback. A student-submitted program is aligned and composed with a reference solution in terms of control flow, and the variables of the two programs are automatically aligned via predicates describing the relationship between the variables. When verification attempt for the obtained aligned program fails, we turn a verification problem into a MaxSMT problem whose solution leads to a minimal repair. We have conducted experiments on student assignments curated from a widely deployed intelligent tutoring system. Our results show that generating verified repair without sacrificing the overall repair rate is possible. In fact, our implementation, Verifix, is shown to outperform Clara, a state-of-the-art tool, in terms of repair rate. This shows the promise of using verified repair to generate high confidence feedback in programming pedagogy settings.

Can automated adaptive feedback for correcting erroneous programs help novice programmers learn to code better? In a large-scale experiment, we compare student performance when tutored by human tutors, and when receiving automated adaptive feedback. The automated feedback was designed using one of two well-known instructional principles: (i) presenting the correct solution for the immediate problem, or (ii) presenting generated examples or analogies that guide towards the correct solution. We report empirical results from a large-scale (N = 480, 10,000 + person hour) experiment assessing the efficacy of these automated compilation-error feedback tools. Using the survival analysis on error rates of students measured over seven weeks, we found that automated feedback allows students to resolve errors in their code more efficiently than students receiving manual feedback. However, we also found that this advantage is primarily logistical and not conceptual; the performance benefit seen during lab assignments disappeared during exams wherein feedback of any kind was withdrawn. We further found that the performance advantage of automated feedback over human tutors increases with problem complexity, and that feedback via example and specific repair have distinct, non-overlapping relative advantages for different categories of programming errors. Our results offer a clear and granular delimitation of the pedagogical benefits of automated feedback in teaching programming to novices.

We present TEGCER, an automated feedback tool for novice programmers. TEGCER uses supervised classification to match compilation errors in new code submissions with relevant pre-existing errors, submitted by other students before. The dense neural network used to perform this classification task is trained on 15000+ error-repair code examples. The proposed model yields a test set classification Pred@3 accuracy of 97.7% across 212 error category labels. Using this model as its base, TEGCER presents students with the closest relevant examples of solutions for their specific error on demand., To appear in 34th IEEE/ACM International Conference on Automated Software Engineering (ASE 2019)

Automated program repair has been used to provide feedback for incorrect student programming assignments, since program repair captures the code modification needed to make a given buggy program pass a given test-suite. Existing student feedback generation techniques are limited because they either require manual effort in the form of providing an error model, or require a large number of correct student submissions to learn from, or suffer from lack of scalability and accuracy. In this work, we propose a fully automated approach for generating student program repairs in real-time. This is achieved by first re-factoring all available correct solutions to semantically equivalent solutions. Given an incorrect program, we match the program with the closest matching refactored program based on its control flow structure. Subsequently, we infer the input-output specifications of the incorrect program's basic blocks from the executions of the correct program's aligned basic blocks. Finally, these specifications are used to modify the blocks of the incorrect program via search-based synthesis. Our dataset consists of almost 1,800 real-life incorrect Python program submissions from 361 students for an introductory programming course at a large public university. Our experimental results suggest that our method is more effective and efficient than recently proposed feedback generation approaches. About 30% of the patches produced by our tool Refactory are smaller than those produced by the state-of-art tool Clara, and can be produced given fewer correct solutions (often a single correct solution) and in a shorter time. We opine that our method is applicable not only to programming assignments, and could be seen as a general-purpose program repair method that can achieve good results with just a single correct reference solution.

Despite the fact an intelligent tutoring system for programming (ITSP) education has long attracted interest, its widespread use has been hindered by the difficulty of generating personalized feedback automatically. Meanwhile, automated program repair (APR) is an emerging new technology that automatically fixes software bugs, and it has been shown that APR can fix the bugs of large real-world software. In this paper, we study the feasibility of marrying intelligent programming tutoring and APR. We perform our feasibility study with four state-of-the-art APR tools (GenProg, AE, Angelix, and Prophet), and 661 programs written by the students taking an introductory programming course. We found that when APR tools are used out of the box, only about 30% of the programs in our dataset are repaired. This low repair rate is largely due to the student programs often being significantly incorrect - in contrast, professional software for which APR was successfully applied typically fails only a small portion of tests. To bridge this gap, we adopt in APR a new repair policy akin to the hint generation policy employed in the existing ITSP. This new repair policy admits partial repairs that address part of failing tests, which results in 84% improvement of repair rate. We also performed a user study with 263 novice students and 37 graders, and identified an understudied problem; while novice students do not seem to know how to effectively make use of generated repairs as hints, the graders do seem to gain benefits from repairs.

We use state-of-the-art parsing technology to build GeoSynth --- a system that can automatically solve word problems in geometric constructions. Through our experiments we show that even though off-the-shelf parsers perform poorly on texts containing specialized vocabulary and long sentences, appropriate preprocessing of text before applying the parser and use of extensive domain knowledge while interpreting the parse tree can together help us circumvent parser errors and build robust domain specific natural language understanding modules useful for various educational applications.