Edutex

Context-aware Learning Analytics with Smart Wearables

Edutex evolved at the beginning of the pandemic out of a desire to discover more about the physical context of learners in distance education without losing track of data protection. In order to be able to support learners in the near future in their custom physical learning environment and in their individual home learning processes with the help of adaptive interventions, we have decided on the integration of commodity smartphones and smartwatches. In current studies, we used the Edutex Android smartphone and smartwatch apps to integrate their sensor data combined with questionnaire data obtained on the devices with learning management system data. We are currently exploring artificial intelligence methods to analyze the resulting multi-modal data stream, including through time series analysis, to provide just-in-time adaptive interventions in teacher dashboards or on learner smart wearables in the future.

How the System Software Architecture looks like

The design differentiates between the client-side part and the server-side part. The client-side comprises modules for data acquisition and data usage. The server-side encapsulates the processing logic for data acquisition and data usage as well as data curation, data analysis, and storage.

What Services Edutex Offers

Edutex was designed and developed as a plug-and-play software infrastructure. Commonly available and free technology was used for administration, configuration and operation.

Participant Management

Participants can be managed in a Django served administration interface.

Study Configuration

The configuration of studies including the sensor acquisition and the questionnaire setup can be done online.

Data Export

Collected data can be downloaded via API services at the session, participant, and study levels.

User Feedback Dashboard

In a dashboard, users can review their data traces and give feedback on session and activity level.

Automated or User-controlled Tracking

The data tracking can be triggered automated based on learning management system activeness or user-controlled on the devices.