@article{cui_zhang_li_zhou_song_gehringer_2024, title={How Pre-class Programming Experience Influences Students' Contribution to Their Team Project: A Statistical Study}, url={https://doi.org/10.1145/3626252.3630870}, DOI={10.1145/3626252.3630870}, abstractNote={Group or team projects are an essential component of the software engineering curriculum. Earlier studies have explored how prior programming experience influences students' team project performance and overall class performance in software engineering. However, few studies address the impact of prior programming experience on students' contributions to team projects. Previous work has varied in its definitions of prior programming experience or skill, leading to inconsistent findings. In this study, we collected pre-class GitHub contribution metrics from 237 students (forming 79 teams of three) across two academic years to measure their prior programming experience and skills. We also mined students' project repositories' git logs to collect individual student contributions. A central question revolved around whether students with more substantial prior programming experience were indeed more active contributors to their project teams. Interestingly, our data indicated a positive correlation between prior programming experience and contributions to team projects. We further delved into team dynamics. Specifically, we questioned if teams made up of members with comparable skill levels exhibited a more even distribution of contributions. Contrary to expectations, our findings revealed no association between these two variables. Moreover, we investigated the team configurations that might encourage the rise of "free riders"-students who contributed only minimally. This paper seeks to augment the body of research on computing education and assist educators in understanding how prior programming experience impacts students' contributions in team projects.}, journal={PROCEEDINGS OF THE 55TH ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION, SIGCSE 2024, VOL. 1}, author={Cui, Jialin and Zhang, Runqiu and Li, Ruochi and Zhou, Fangtong and Song, Yang and Gehringer, Edward}, year={2024}, pages={255–261} }
 @article{cui_zhang_li_song_zhou_gehringer_2023, title={Correlating Students' Class Performance Based on GitHub Metrics: A Statistical Study}, url={https://doi.org/10.1145/3587102.3588799}, DOI={10.1145/3587102.3588799}, abstractNote={What skills does a student need to succeed in a programming class? Ostensibly, previous programming experience may affect a student's performance. Most past studies on this topic use self-reporting questionnaires to query students about their programming experience. This paper presents a novel, unified, and replicable way to measure previous programming experience using students' pre-class GitHub contributions. To our knowledge, we are the first to use GitHub contributions in this way. We conducted a comprehensive statistical study of students in an object-oriented design and development class from 2017 to 2022 (n = 751) to explore the relationships between GitHub contributions (commits, comments, pull requests, etc.) and students' performance on exams, projects, designs, etc. in the class. Several kinds of contributions were shown to have statistically significant correlations with performance in the class. A set of two-samplet -tests demonstrate statistical significance of the difference between the means of some contributions from the high-performing and low-performing groups.}, journal={PROCEEDINGS OF THE 2023 CONFERENCE ON INNOVATION AND TECHNOLOGY IN COMPUTER SCIENCE EDUCATION, ITICSE 2023, VOL 1}, author={Cui, Jialin and Zhang, Runqiu and Li, Ruochi and Song, Yang and Zhou, Fangtong and Gehringer, Edward}, year={2023}, pages={526–532} }
 @article{cui_li_lou_liu_xiao_jia_gehringer_zhang_2022, title={Can Pre-class GitHub Contributions Predict Success by Student Teams?}, DOI={10.1109/ICSE-SEET55299.2022.9794264}, abstractNote={Over one million teachers, students, and schools around the world use GitHub to reach their learning goals. GitHub promotes team-work, and group or team projects are a necessary element of the software-engineering curriculum. Past studies on GitHub have explored how to integrate GitHub into teaching and how to mine information from GitHub to help students. To our knowledge, we are the first to study the previous contributions of students to GitHub in order to characterize student teams that perform well on team projects, compared to student teams that did not perform so well. We identify factors such as the number of public commits, number of repositories, and size of repositories in certain languages that are associated with the quality of team projects. We discuss the implications of this from the point of view of an educator and a student.}, journal={2022 ACM/IEEE 44TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: SOFTWARE ENGINEERING EDUCATION AND TRAINING (ICSE-SEET 2022)}, author={Cui, Jialin and Li, Ruochi and Lou, Kaida and Liu, Chengyuan and Xiao, Yunkai and Jia, Qinjin and Gehringer, Edward and Zhang, Runqiu}, year={2022}, pages={40–49} }
 @inproceedings{xiao_wang_sun_li_song_cui_jia_liu_gehringer_2022, title={Modeling review helpfulness with augmented transformer neural networks}, ISSN={["2325-6516"]}, DOI={10.1109/ICSC52841.2022.00019}, abstractNote={The past two years have witnessed a dramatic change in the delivery of education, as most providers have pivoted to remote online learning. With the enrollment of some MOOCs platforms, for example, Coursera, going up by 444% between mid-March and mid-September 202011Coursera 2020 Impact Report: https://about.coursera.org/press/wpcontent/uploads/2020/09/Coursera-Impact-Report-2020.pdf, practical teaching on a large scale attracted significant attention from the public. For online educators, this was manifested as a significant increase in assessment workload. MOOC instructors have long used peer assessment to evaluate work submitted by online learners. Prior research has shown that when a student believes feedback is helpful, then the suggestion given by that feedback is more likely to be implemented. Researchers have studied machine learning models for detecting problem statements or suggestions in feedback. However, these models do not work as well in detecting secondary features like helpfulness. This paper introduces a new augmented model for detecting helpfulness and tests it against the original model that uses raw text, yielding a 7% increase in performance measured in F1 score.}, booktitle={2022 IEEE 16th International Conference on Semantic Computing (ICSC)}, author={Xiao, Yunkai and Wang, Tianle and Sun, Xinhua and Li, Licong and Song, Yang and Cui, Jialin and Jia, Qinjin and Liu, Chengyuan and Gehringer, Edward}, year={2022}, pages={83–90} }
 @article{shen_pielke sr_zeng_cui_faghih-naini_paxson_kesarkar_zeng_atlas_2022, title={The Dual Nature of Chaos and Order in the Atmosphere}, volume={13}, ISSN={["2073-4433"]}, DOI={10.3390/atmos13111892}, abstractNote={In the past, the Lorenz 1963 and 1969 models have been applied for revealing the chaotic nature of weather and climate and for estimating the atmospheric predictability limit. Recently, an in-depth analysis of classical Lorenz 1963 models and newly developed, generalized Lorenz models suggested a revised view that “the entirety of weather possesses a dual nature of chaos and order with distinct predictability”, in contrast to the conventional view of “weather is chaotic”. The distinct predictability associated with attractor coexistence suggests limited predictability for chaotic solutions and unlimited predictability (or up to their lifetime) for non-chaotic solutions. Such a view is also supported by a recent analysis of the Lorenz 1969 model that is capable of producing both unstable and stable solutions. While the alternative appearance of two kinds of attractor coexistence was previously illustrated, in this study, multistability (for attractor coexistence) and monostability (for single type solutions) are further discussed using kayaking and skiing as an analogy. Using a slowly varying, periodic heating parameter, we additionally emphasize the predictable nature of recurrence for slowly varying solutions and a less predictable (or unpredictable) nature for the onset for emerging solutions (defined as the exact timing for the transition from a chaotic solution to a non-chaotic limit cycle type solution). As a result, we refined the revised view outlined above to: “The atmosphere possesses chaos and order; it includes, as examples, emerging organized systems (such as tornadoes) and time varying forcing from recurrent seasons”. In addition to diurnal and annual cycles, examples of non-chaotic weather systems, as previously documented, are provided to support the revised view.}, number={11}, journal={ATMOSPHERE}, author={Shen, Bo-Wen and Pielke Sr, Roger and Zeng, Xubin and Cui, Jialin and Faghih-Naini, Sara and Paxson, Wei and Kesarkar, Amit and Zeng, Xiping and Atlas, Robert}, year={2022}, month={Nov} }
 @article{cui_shen_2021, title={A kernel principal component analysis of coexisting attractors within a generalized Lorenz model}, volume={146}, ISSN={["1873-2887"]}, DOI={10.1016/j.chaos.2021.110865}, abstractNote={Based on recent studies that reveal the coexistence of chaotic and non-chaotic solutions using a generalized Lorenz model (GLM), a revised view on the dual nature of weather has been proposed by Shen et al. [41,42], as follows: the entirety of weather is a superset consisting of both chaotic and non-chaotic processes. Since better predictability for non-chaotic processes can be expected, an effective detection of regular or chaotic solutions can improve our confidence in numerical weather and climate predictions. In this study, by performing a kernel principal component analysis of coexisting attractors obtained from the GLM, we illustrate that the time evolution of the first eigenvector of the kernel matrix, referred to as the first kernel principal component (K-PC), is effective for the classification of chaotic and non-chaotic orbits. The spatial distribution of the first K-PC within a two-dimensional phase space can depict the shape of a decision boundary that separates the chaotic and non-chaotic orbits. We additionally present how a large number (e.g., 128 or 256) of K-PCs can be used for the reconstruction of data in order to illustrate the different portions of the phase space occupied by chaotic and non-chaotic orbits, respectively.}, journal={CHAOS SOLITONS & FRACTALS}, author={Cui, Jialin and Shen, Bo-Wen}, year={2021}, month={May} }