Learning analytics

This project is aimed to do collaborative research and open innovation in the field of learning analytics. It is being carried out by UPCnet, along with some other research groups and inLab FIB, to enhance and transfer knowledge on the subject, in order to promote innovation, improvement capability and competitiveness of the services and products UPCnet offers in the scope of learning processes (e-Learning and Virtual Campuses) and their management.

The learning analytics field of research combines techniques such as educational data mining, business intelligence, social networks analysis, sentiment analysis or educational data conceptual modelling to gather information and knowledge about the operation and results of an educational system at different levels. These methods allow us to detect and interpret symptoms from available data and digital traces, as well as adapt the system's behaviour properly. An application example is the early detection and identification of students who need special help or are in risk of failure, to adapt learning tools or to suggest the needed decisions to be taken.

Even though it is a vast research area that demands huge amounts of efforts and time to be fully addressed, a series of initial goals will be set to be accomplished in the scope of the project. These goals will be reviewed and prioritized periodically.

The main areas that are wanted to be explored are:

• Definition of learning results indicators, at different levels, ranging from system-global scope (addressed to the educational authorities) to individuals, as well as at institution scale.
• Data gathering, integration and modelling
  • Analysis of data available in Moodle based virtual campuses
  • Plugins and other existing moodle tools to offer indicators of the courses monitoring.
  • Analyisis of other information sources like the results of the various competences exams or studying management systems.
  • Information conceptual modelling.
  • Integration of data coming from different sources into a single conceptual model.
• Educational data mining in order to analize the available data to obtain and infer the desired indicators to answer information needs.
• Intuitive visualization tools addressed to students, professors and managers, along with the development of a management board for the educational authorities to use.
• Technological monitoring of learning analytics usage in other places or scopes.
• Relation with adaptative and personalized learning tools.