Using learning analytics to investigate and support collaborative learning
has been explored for many years. Recently, automated approaches with various
artificial intelligence approaches have provided promising results for
modelling and predicting student engagement and performance in collaborative
learning tasks. However, due to the lack of transparency and interpretability
caused by the use of “black box” approaches in learning analytics design and
implementation, guidance for teaching and learning practice may become a
challenge. On the one hand, the black box created by machine learning
algorithms and models prevents users from obtaining educationally meaningful
learning and teaching suggestions. On the other hand, focusing on group and
cohort level analysis only can make it difficult to provide specific support
for individual students working in collaborative groups. This paper proposes a
transparent approach to automatically detect student’s individual engagement in
the process of collaboration. The results show that the proposed approach can
reflect student’s individual engagement and can be used as an indicator to
distinguish students with different collaborative learning challenges
(cognitive, behavioural and emotional) and learning outcomes. The potential of
the proposed collaboration analytics approach for scaffolding collaborative
learning practice in face-to-face contexts is discussed and future research
suggestions are provided.
Using Learning Analytics in Collaborative Learning
The use of learning analytics in collaborative learning has been a topic of study for many years. Learning analytics refers to the collection, analysis, and interpretation of data from educational activities to improve teaching and learning outcomes. In recent years, automated approaches with artificial intelligence have shown promising results in modeling and predicting student engagement and performance in collaborative learning tasks.
However, there is a challenge in using automated approaches due to the lack of transparency and interpretability caused by the use of “black box” algorithms. These algorithms, while effective in predicting outcomes, do not provide meaningful insights or suggestions to educators.
One of the difficulties with current approaches is the focus on group and cohort level analysis, which can make it challenging to provide specific support for individual students in collaborative groups. This is where the proposed transparent approach comes into play.
A Transparent Approach to Detecting Individual Engagement
This paper proposes a transparent approach to automatically detect a student’s individual engagement in the process of collaboration. By making the process transparent, educators can gain meaningful insights into students’ collaborative learning challenges and outcomes.
The results of the study show that the proposed approach effectively reflects a student’s individual engagement and can be used as an indicator to distinguish between students facing different collaborative learning challenges, such as cognitive, behavioral, and emotional difficulties. Additionally, it can also predict learning outcomes.
The Multidisciplinary Nature of Collaboration Analytics
The proposed approach highlights the multidisciplinary nature of collaboration analytics. It combines techniques from fields such as artificial intelligence, education, psychology, and data analytics to provide a holistic understanding of collaborative learning processes. This multidisciplinary approach allows for a more comprehensive assessment of student engagement and learning outcomes.
Implications for Teaching and Learning Practice
The transparency of the proposed approach allows for more informed teaching and learning practice. Educators can use the insights gained from collaboration analytics to provide targeted support to individual students facing collaborative learning challenges. This personalized approach can enhance students’ learning experiences and improve outcomes.
Furthermore, the proposed approach has the potential to scaffold collaborative learning practice in face-to-face contexts. By providing real-time feedback on students’ engagement, educators can intervene and guide the collaborative process as needed. This can lead to more effective collaboration and improved learning outcomes.
Future Research Directions
While the proposed approach shows promise, there is still room for further research and development. Future research should focus on validating the approach in different educational contexts, exploring additional factors influencing collaboration, and refining the analytics models to improve accuracy and interpretability.
In conclusion, the use of learning analytics in collaborative learning has the potential to revolutionize teaching and learning practices. The proposed transparent approach offers a way to overcome the limitations of “black box” algorithms and provides meaningful insights into student engagement and learning outcomes. By harnessing the multidisciplinary nature of collaboration analytics, educators can support individual students and improve collaborative learning experiences.