Using Learning Analytics to Visualise Computer Science Teamwork

Abstract

Industry has called upon academia to better prepare Computer Science graduates for teamwork, especially in developing the soft skills necessary for collaborative work. However, the teaching and assessment of teamwork is not easy, with instructors being pressed for time and a lack of tools available to efficiently analyse student teamwork, where large cohorts are involved.We have developed a teamwork dashboard, founded on learning analytics, learning theory and teamwork models that analyses students' online teamwork discussion data and visualises the team mood, role distribution and emotional climate. This tool allows educators to easily monitor teams in real-time. Educators may use the tool to provide students with feedback about team interactions as well as to identify problematic teams. We present a case study, trialing the dashboard on one university Computer Science course and include reflections from the course lecturer to determine its utility in monitoring online student teamwork.

Beyond First Encounters with Analytics: Questions, Techniques and Challenges in Instructors’ Sensemaking

“…As a starting point, questions play a critical role in guiding instructors in what data to look for and the kind of meaning to draw from it [30]. Despite the powerful frame that questions can offer, several studies have found that instructors do not always come to analytics use with specified questions [18,25,31]. For instance, Wise & Jung [31], who conducted interviews with five first-time users of an analytic dashboard, found that instructors came to analytics with a general curiosity and only started to specify questions over time as they interacted with analytics to learn what data was available and notice patterns in them.…”

Teaching with Analytics: Towards a Situated Model of Instructional Decision-Making

“…For instance, Dazo, Stepanek, Chauhan, and Dorn (2017) found a low frequency and overall levels of usage of an analytics dashboard for an online video and annotation system by 14 instructors given access for the course of a year. Tarmazdi, Vivian, Szabo, Falkner, and Falkner (2015) investigated a single instructor's use of a teamwork dashboard during a single semester, finding that the instructor used the sentiment analysis graph and the team role analysis features most regularly. Across these studies, a common issue that arose was instructor difficulties in integrating the use of the analytic tools into their daily teaching activities.…”

What Do You Mean by Collaboration Analytics? A Conceptual Model

“…While CSCL theory played a critical role in this case, alternative theoretical underpinnings may be found in team science and CSCW literature, or in theoretical perspectives that define what effective teamwork is in a particular professional domain. For example, Tarmazdi, Vivian, Szabo, Falkner, and Falkner (2015) created a dashboard that automatically identified emerging team roles from online discussions based on a conceptual framework for self-organizing teams, while Wu, Waber, Aral, Brynjolfsson, and Pentland (2008) combined information richness and social network theories to model sensor data to predict team productivity in face-to-face workplace settings. Cases 2 and 3 (explained below) were informed by both educational theories and theoretical foundations relevant to the professional skills that students needed to develop in the contexts of healthcare and urban planning, respectively.…”