Utilizing Big Data to Understand and Improve Student Collaboration in Group Projects
Year: 2026
Type: conference-paper
Abstract: Big data analytics in education have rapidly evolved in recent times, contributing to a dramatic transformation of the teachers’ and institutions’ understanding of student learning practices, especially when applied to collaborative group work. Group projects do not only teach individual learners particular skill-sets (i.e. how to assemble a video in Premiere Pro), they also teach collaboration, communication, and problem solving, three highly applicable elements of the contemporary institution. However, it has been difficult to measure to what extent the cooperation among such groups was good and dynamic. This paper examines how big data has a chance to result in more profound knowledge of student collaboration such that this knowledge may be applied to the creation of more desirable group processes and learning. Education Big Data is the rich data that is gathered from any of the digital resources that you use to educate your students; Learning Management Systems, Collaborative Collaboration Tools, Discussion Forums, Submissions, and Peer Review. The pattern of participation, communication channel flow, and task allocation of the individuals comprising the group can be found as a result of analyzing these datasets. These insights can open the door of a more objective, real-time and systemic understanding about how collaboration really happens in practice in contrast to (for instance) observation- or self-reported methods. It further points to how data-driven approaches can be used to identify the gaps and difference in engagement of teams. For example, learning analytics can be used to identify passive contributors, members that has too much to do or the failure in communication at an early stage in the project schedule. With this information in hand, teachers will be able to address students as needed to provide timely feedback, support learners, and redistribute tasks so that all members of the group participate equally and maximize the outcome of the group effort. Moreover, machine learning technologies can forecast the outcomes of the project and propose the best groups according to the previous patterns of behavior, abilities, and history of collaboration of the student. Another significant observation that may be made in this research is the ethical dimension that is emerging out of the imposition of the information on the students. Above all, it emphasises the need for privacy, consent and transparency in the collection and analysis of shared data. Data governance policies and ethical standards at the institution should be taken seriously and big data tools implemented to earn stakeholder trust.
Institution: Fergana State Technical University
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7203713873