Research

Program comprehension, code summarization, and generative AI in software engineering education

Software engineering and program comprehension

Most of my work asks how programmers understand code they did not write, and how to generate the documentation they need. With Prof. Collin McMillan, my PhD advisor, at Notre Dame I built one of the first neural models that writes commit messages from diffs (ASE 2017) and a model that summarizes subroutines in natural language (ICSE 2019). Earlier, I studied how programmers do change impact analysis while debugging (Empirical Software Engineering, 2017). My most recent paper, with two EMU master's students, measures how documentation in pull requests affects whether contributors engage with tests (FSE 2026).

Generative AI in software engineering education

In collaboration with Dr. Allan Brockenbrough from Salem State University, we ran a study across two universities in which 48 students wrote 406 user stories with guided help from a generative AI tool. We scored each story on the seven INVEST attributes.

Allan Brockenbrough, Yasrib Yasir Farook, Teal Amore, and Siyuan Jiang, "Guiding Students in Using Generative AI for User Story Writing: An Experience Report", in Proc. of the 2nd ACM Virtual Global Computing Education Conference (SIGCSE Virtual 2026). doi:10.1145/3795867.3831003

Research assistants: Teal Amore and Yasrib Yasir Farook.

How neurodivergent people learn computer science

This is my current direction and I use "neurodivergent" broadly. It includes people who learn differently under stress or depression, with or without a diagnosis. I am developing this work in two settings.

Younger learners, in camps. In 2025 I ran a Scratch pilot. In July 2026 I ran a three-day, sensory-friendly LEGO SPIKE Prime camp for nine students in grades 6 to 12. A 2027 camp is in preparation: with Dr. Sarah Quinn from Special Education at EMU as co-investigator, I have applied to the Michigan Space Grant Consortium to fund it, and she leads the evaluation of the camp.

Undergraduate assistants: Salma Ibrahim, Sasha Odumodu, and Yasrib Yasir Farook.

Literature review of existing studies. With a team of undergraduate researchers and collaborating with Dr. Sarah Quinn from Special Education at EMU, I am conducting a systematic literature review of computer science education for neurodivergent students.

Undergraduate assistants: Rataj Albalawi, Maryam Judeh, Ammar Owis, Sarah Taher, Yasrib Yasir Farook, Salma Ibrahim, and Ishaq Ahmed.

Publications

2027Kaitlyn Tracy, Siyuan Jiang, and Ourania Spantidi, "What Do Students Want From a General Education AI Course? A Student-Informed Design", poster in Proc. of the 58th ACM Technical Symposium on Computer Science Education (SIGCSE TS 2027), accepted.
2026Teal Amore, Nathan Berman, and Siyuan Jiang, "The Impact of Documentation on Test Engagement in Pull Requests in OSS", in Proc. of the ACM International Conference on the Foundations of Software Engineering (FSE'26), Montreal, Canada.
2026Allan Brockenbrough, Yasrib Yasir Farook, Teal Amore, and Siyuan Jiang, "Guiding Students in Using Generative AI for User Story Writing: An Experience Report", in Proc. of the 2nd ACM Virtual Global Computing Education Conference (SIGCSE Virtual 2026). doi:10.1145/3795867.3831003
2024Anthony Varkey, Siyuan Jiang, and Weijing Huang, "CodeCSE: A Simple Multilingual Model for Code and Comment Sentence Embeddings", arXiv preprint arXiv:2407.06360.
2023Aakash Bansal, Siyuan Jiang, Sakib Haque, and Collin McMillan, "Statement-based Memory for Neural Source Code Summarization", arXiv preprint arXiv:2307.11709.
2019Alexander LeClair, Siyuan Jiang, and Collin McMillan, "A Neural Model for Generating Natural Language Summaries of Program Subroutines", in Proc. of the 41st ACM/IEEE International Conference on Software Engineering (ICSE'19), Montreal, Canada.
2019Yihao Huang, Jincao Feng, Hanyue Zheng, Jiayi Zhu, Shang Wang, Siyuan Jiang, Weikai Miao, and Geguang Pu, "Prema: A Tool for Precise Requirements Editing, Modeling and Analysis", in Proc. of the 34th IEEE/ACM International Conference on Automated Software Engineering, Demonstrations Track (ASE'19), San Diego, California, USA.
2017Siyuan Jiang, Ameer Armaly, and Collin McMillan, "Automatically Generating Commit Messages from Diffs Using Neural Machine Translation", in Proc. of the 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE'17), Urbana-Champaign, Illinois, USA.
2017Rrezarta Krasniqi, Siyuan Jiang, and Collin McMillan, "TraceLab Components for Generating Extractive Summaries of User Stories", in Proc. of the 33rd IEEE International Conference on Software Maintenance and Evolution, Artifacts Track (ICSME'17), Shanghai, China.
2017Paul W. McBurney, Siyuan Jiang, Marouane Kessentini, Nicholas A. Kraft, Ameer Armaly, Mohamed Wiem Mkaouer, and Collin McMillan, "Towards Prioritizing Documentation Effort", in IEEE Transactions on Software Engineering (TSE), vol. 44, no. 9, pp. 897-913, 2018. Journal-First paper presentation at the 11th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering (ESEC/FSE'17), Paderborn, Germany.
2017Siyuan Jiang and Collin McMillan, "Towards Automatic Generation of Short Summaries of Commits", in Proc. of the 25th International Conference on Program Comprehension, Early Research Achievement Track (ICPC'17), Buenos Aires, Argentina.
2017Siyuan Jiang, Ameer Armaly, Collin McMillan, Qiyu Zhi, and Ronald Metoyer, "Docio: Documenting API Input/Output Examples for C Libraries", in Proc. of the 25th International Conference on Program Comprehension, Tool Demo Track (ICPC'17), Buenos Aires, Argentina.
2017Paige Rodeghero, Siyuan Jiang, Ameer Armaly, and Collin McMillan, "Detecting User Story Information in Developer-Client Conversations to Generate Extractive Summaries", in Proc. of the 39th ACM/IEEE International Conference on Software Engineering (ICSE'17), Buenos Aires, Argentina.
2016Siyuan Jiang, Collin McMillan, and Raul Santelices, "Do Programmers Do Change Impact Analysis in Debugging?", in Empirical Software Engineering (EMSE), vol. 22, no. 2, April 2017, pp. 631-669. Journal-First paper presentation at the 33rd IEEE International Conference on Software Maintenance and Evolution (ICSME'17), Shanghai, China.
2016Haipeng Cai, Raul Santelices, and Siyuan Jiang, "Prioritizing Change-Impact Analysis via Semantic Program-Dependence Quantification", in IEEE Transactions on Reliability, vol. 65, no. 3, pp. 1114-1132.
2014Raul Santelices, Haipeng Cai, Siyuan Jiang, and Yiji Zhang, "Advanced Dependence Analysis for Software Testing, Debugging, and Evolution", in IEEE Reliability Digest, November, pp. 18-24.
2014Siyuan Jiang, Raul Santelices, Mark Grechanik, and Haipeng Cai, "On the Accuracy of Forward Dynamic Slicing and its Effects on Software Maintenance", in Proc. of the 14th IEEE International Conference on Source Code Analysis and Manipulation (SCAM'14), Victoria, BC, Canada.
2014Haipeng Cai, Siyuan Jiang, Raul Santelices, Ying-Jie Zhang, and Yiji Zhang, "SENSA: Sensitivity Analysis for Quantitative Change-Impact Prediction", in Proc. of the 14th IEEE International Conference on Source Code Analysis and Manipulation (SCAM'14), Victoria, BC, Canada.
2014Siyuan Jiang, Raul Santelices, Haipeng Cai, and Mark Grechanik, "How Accurate Is Dynamic Program Slicing? An Empirical Approach to Compute Accuracy Bounds", in Proc. of the 8th IEEE International Conference on Software Security and Reliability, Companion, San Francisco, CA, USA.
2014Ting Su, Geguang Pu, Bin Fang, Jifeng He, Jun Yan, Siyuan Jiang, and Jianjun Zhao, "Automated Coverage-Driven Test Data Generation Using Dynamic Symbolic Execution", in Proc. of the 8th International Conference on Software Security and Reliability, San Francisco, CA, USA.
2014Raul Santelices, Yiji Zhang, Haipeng Cai, and Siyuan Jiang, "Change-Effects Analysis for Evolving Software", in Advances in Computers, vol. 93, ch. 5, pp. 227-285.
2013Raul Santelices, Yiji Zhang, Siyuan Jiang, Haipeng Cai, and Ying-Jie Zhang, "Quantitative Program Slicing: Separating Statements by Relevance", in Proc. of the 35th International Conference on Software Engineering, New Ideas and Emerging Results Track (ICSE'13), San Francisco, CA, USA.
2013Raul Santelices, Yiji Zhang, Haipeng Cai, and Siyuan Jiang, "DUA-Forensics: A Fine-Grained Dependence Analysis and Instrumentation Framework Based on Soot", in Proc. of the 2nd ACM SIGPLAN International Workshop on the State of the Art in Java Program Analysis, Seattle, WA, USA.
2011Xiao Yu, Shuai Sun, Geguang Pu, Siyuan Jiang, and Zheng Wang, "A Parallel Approach to Concolic Testing with Low-cost Synchronization", in Electronic Notes in Theoretical Computer Science, vol. 274, pp. 83-96.

Student research

2026Yasrib Yasir Farook (undergraduate), Undergraduate Research Stimulus Program: Better Learning of Software Requirement Writing with ChatGPT.
2026Ishaq Ahmed (undergraduate), Undergraduate Research Stimulus Program: Systematic Literature Review of Teaching Practices and Methods for Students with Disabilities in Computer Science.
2023Mohammad Arjamand Ali (undergraduate), EMU Symposium Undergraduate Research Fellowship and Honors Research Fellowship, 2023 to 2024.
2022Ke Shao (undergraduate), independent study: CPU/GPU parallel programming for computational fluid dynamics.
2021Jonathan Nemchak (undergraduate), independent study: workout and health tracker.
2020Stephen Rice (master's thesis): An Application of a RoBERTa-like Language Model Pre-trained Using a Punctuation Prediction Task.
2019Alexander London and May Le (undergraduate research).