Using Sequence Analysis to Determine the Well-Functioning of Small Groups in Large Online Courses

Abstract

Collaborative learning in small groups can enrich and enhance the learning experience in large online courses by facilitating interaction and collaborative knowledge building between peers. on the work reported here addresses scenarios based on asynchronous communication and exchange. As compared to synchronous and face-to-face settings, these scenarios require higher explicit coordination efforts and specific support mechanisms to reach out to inactive group members. This can be achieved by human tutors as well as through automatic interventions by the system in the organization and facilitation of group work. Our approach is based on characterizing the quality or well-functioning of collaboration using sequence alignment techniques that were originally developed in bioinformatics for the comparison of DNA sequences. Sequence alignment provides a similarity measure between pairs of action logs originating from the group work. The ensuing similarity matrix allows for clustering the working groups characterized by the similarity of their complete action logs. Notably, these clusters differ clearly in terms of quality measures related to the activity distribution and group output. This allows for determining quality indicators that can trigger feedback and adaptive scaffolding. Our data stem from inter-university online courses in which regular (weekly or bi-weekly) assignments had to be completed in small groups supported by an online forum for coordination and a separate tool for the actual collaborative writing. The basic actions are interpreted/coded as different contribution types, namely coordination, monitoring, minor/major contributions. Longer periods of inactivity are coded as another type of action (“gap”). These are the building blocks for the sequence alignment. One consequence of our analysis is a revision of the intuitive assumption that inactivity is a main indicator of inefficient group work: We found that inactivity can be compensated by early coordination to the extent that coordination is even the most important factor for successful group work. These insights are now being used to design alert mechanisms to signal inefficient group work and to generate timely interventions.

An artificial intelligence-driven learning analytics method to examine the collaborative problem-solving process from the complex adaptive systems perspective

“…Furthermore, CPS is a dynamic process, where the relations between elements change over time, and ultimately affect the quality of collaboration (Holland, 1996;Hoppe et al, 2021;Koopmans & Stamovlasis, 2016;Saqr & López-Pernas, 2022). During the CPS process, students are required to adjust and coordinate interaction, behaviour, cognition, and emotional contributions to the evolving task context.…”

“…For example, HMMs have the potential to capture the stable, distinct states of CPS as well as dynamic movements between and within them, which has the particular ability to reveal the adaptive, self-organizing character of collaborative learning. Furthermore, advanced AI algorithms (e.g., multidimensional recurrence quantification analysis, natural language processing, genetic programming) have been applied in CSCL to analyze and reveal the complexity and dynamics of collaboration (Amon et al, 2019;de Carvalho & Zárate, 2020;Hoppe et al, 2021;Sullivan & Keith, 2019). Future work can further integrate these advanced AI algorithms with learning analytics and data mining to reveal the multilevel, multidimensional characteristics of CSCL.…”

Integration of artificial intelligence performance prediction and learning analytics to improve student learning in online engineering course

“…The current work integrated AI and LA approaches with both performance and process data to reveal the characteristics of student groups’ collaborative learning. Future work can use advanced AI algorithms (e.g., natural language processing, genetic programming) with learning analytics and data mining to offer in-time, multidimensional characteristics of collaborative learning (Amon et al, 2019 ; de Carvalho & Zárate, 2020 ; Hoppe et al, 2021 ). Overall, AI-driven learning analytics and educational data mining has potential to provide feedback on similarities and differences of student performance at the individual and group level to close the loop of AI model development and educational application, with an ultimate goal of improving the instruction and learning quality.…”

Multimodal learning analytics of collaborative patterns during pair programming in higher education

“…Echoing this trend, this research collected student pairs' multimodal data (i.e., verbal audios, computer screen recordings, facial expression recordings, final products data) and applied multiple learning analytics methods (e.g., content analysis, epistemic network analysis, process mining) to investigate the collaborative patterns in PP as well as their quantitative, structural, and transitional characteristics. Furthermore, advanced and automated artificial intelligence (AI) algorithms (e.g., hidden Markov model, natural language processing, recurrence quantification analysis) are advised to analyze the complexity and dynamics of collaboration in the future research (Gorman et al, 2020;Hoppe et al, 2021). Compared to traditional learning analytics methods, AI-driven methods have potential to analyze multimodal and nonlinear data and extract the complex and dynamic structure of CPS (de Carvalho & Zárate, 2020).…”