Research

Computer-delivered assessments make it possible to keep track of students’ response behaviors and interactions with the tasks through gathering process data. Rich information can be obtained from the process data, which has drawn growing attention in educational research, including response time, eye tracking, keystroke, and problem-solving actions and sequences. Process data can reflect students’ problem-solving processes leading up to their final responses and provide information on how students try to accomplish a task rather than merely how well students accomplish a task. Process data comes into play when we need to know more than whether a student answers an item correctly.

Selected publications

• Zhu, M., Zhang, M., & Gu, L. (2023). Insights into editing and revising in writing process using keystroke logs. Language Assessment Quarterly.

• Song, Y., Zhu, M., & Sparks, J. (2023). Exploring the Role of Process Data Analysis in Understanding Student Performance and Interactive Behavior in a Game-based Argument Task. Journal of Educational Computing Research, 61(5), 1096–1120. https://doi.org/10.1177/07356331221138734

• Xu, Q., Chen, N., Tu, J., Liu, X., & Zhu, M. (2023). Teaching Scientific Experiments through Online Video Lectures: An Eye-Tracking Research. Proceeding of the 13th IEEE Integrated STEM Education Conference (March 11, 2023).

• Li, J., Wang, F., Liu, Q., Zhu, M., Huang, W., Huang, Z., Chen, E., Su, Y., & Wang, S. (2022). HierCDF: A Bayesian Network-based Hierarchical Cognitive Diagnosis Framework. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 904–913. https://doi.org/10.1145/3534678.3539486

Collaborative problem solving (CPS) is considered one of the critical competencies for 21st-century talents as increasingly complex tasks emerge in workplace contexts. Therefore, fostering and assessing students’ CPS skills gained increasing academic attention in recent years. 

Selected publications

• Xu, Q., Zhang, B., Wang, J., Liu, X., & Zhu, M. (2023). A Collaborative Learning and Support System for STEM Education and Learning Analytics. Proceeding of the 13th IEEE Integrated STEM Education Conference (March 11, 2023).

• Zhu, M., Xu, Q., Dou, Z., Zhang, L., & Andrews‐Todd, J. (2023). Exploring the Interplay between Domain Knowledge and Collaborative Problem Solving Skills through User Profiling. Proceeding of the Third Annual Meeting of the International Society of the Learning Sciences (June 10-15, 2023).

Many organizations allow some subset of employees in particular functions to work from remote offices, or from their home after training and, typically only after a trial remote-work period. The shift to remote work has been gradual, selective, and limited in scope. However, the academic literature is mixed on the effectiveness of remote work arrangements for collaboration. In addition, in response to dramatic changes, remote work has arrived at unprecedented speed and scale and few people or the companies in which they work are prepared for it. This is being enabled by digital collaboration platforms that allow workers to communicate via text, audio, and video and to share and edit documents in real-time, which can enhance or impede team collaboration. This project explore organizational dynamics as they are unfolding and to compare them with what they were prior to the disruption. 

Selected publications

• Zhu, M., Liu, L., Su, R., & Contractor, N. S. (2023). Revisiting the Effects of Social Networks on Enterprise Collaboration Technology Use: A Fuzzy-set Qualitative Comparative Analysis Approach. Decision Support Systems, 174(114017). https://doi.org/10.1016/j.dss.2023.114017

Leveraging the big data collected from the social media to understand user behaviors and interactions.

Selected publications

• Ji, J., Hu, T., Chen, Z., & Zhu, M. (2024). Exploring the climate change discourse on Chinese social media and the role of social bots. Asian Journal of Communication. https://doi.org/10.1080/01292986.2023.2269423

• Chen, Z., Shen, J., Zhu, M., Hu, B., & Liu, A. (2022). Predicting Virtual Gifting Behaviors in Live Streaming Using Danmaku Information. Proceedings of the 8th International Conference on Big Data Computing and Communications (BigCom 2022). 10.1109/BigCom57025.2022.00032

The Oncofertility Consortium® is a national, interdisciplinary, multi-institutional collaborative team aimed at exploring the reproductive future of cancer survivors.  The goal of the Oncofertility Consortium® is to build a new interdisciplinary field at the intersection of oncology and reproductive medicine.Within the Oncofertility project, SONIC researchers investigate how the collaboration networks of medical specialists, scientists, and scholars evolve in time using both survey and bibliometric data. The survey data has been collected using the C-IKNOW tool, an application developed by the SONIC research group. The intermediary goal is to measure the impact of the Oncofertility Consortium on the growth and continuation of interdisciplinary research and collaborations on issues related to oncofertility.

National Science Foundation, ITR: IT-Based Collaboration Framework for Preparing Against, Responding to, and Recovering from Disasters Involving Critical Physical Infrastructures, (2004-2009, 0427089, $2,370,000) Co-Principal Investigator Noshir Contractor in collaboration with Professors Feniosky Pena-Mora,  Gene E. Robinson, and Indranil Gupta (University of Illinois Urbana-Champaign), and Andrea Hollingshead (University of Southern California).