Abstract:

The role of social media in higher education has shifted from providing a web 2.0 solution for supporting communication in computer supported learning to more advanced functionalities including virtual learning environment tools (e.g. content sharing, threaded discussions). This paper discusses how social media data analysis can equip tutors with visual probes for certain areas that may need attention. The paper also describes how data mining can be used for assessing the source of communication patterns in computer supported collaborative (e.g. issues associated with content, learning activities or student competencies).

The paper attempts to identify certain metrics for the production of a learning analytics dashboard. Current work presented in the paper includes the statistical analysis of communication data between 24 student groups and 66 student pairs from a cohort of more than 120 final year students studying information systems. The data collected from Facebook, Twitter and Linked in have been analysed with the use of NodeXL, demonstrating group cohesion, communication pattern, student interactions and frequency of message exchanges.

Emphasis was given on investigating the total tweets, Facebook posts and LinkedIn projects submitted by students over a period of 24 learning weeks over 7-8 months. The scope of the analysis was to assess how different learning tasks affected individual and group contributions as well as the impact of specific learning activities on tasks such as commenting, sharing, linking and liking. The investigation also considered how keywords were used, indicating how social media interaction was affected by the subjects covered during specific learning weeks.

The authors also present the use of data mining techniques for identifying which metric best predicts the student’s results in terms of engagement, involvement, participation, contribution and communication. These are some of the factors that may affect the learning experience when integrating Web 2.0 technologies with traditional virtual learning environments. Current work discussed in the paper also attempts to use time series data, to test which metrics can predict the student’s results in real time (i.e. identifying those students who are likely to fail or need additional support), as well as ways to analyse social media metrics and suggestions for further work towards implement learning analytics dashboards.

Keywords:

Social media, Web 2.0, learning analytics, data mining for e-learning.