null Automating feedback and assessment through wearables and sensors

OW_21eeuwseVaardigheden_10620_head_large.jpg
Digital Learning
Automating feedback and assessment through wearables and sensors
Daniele Di Mitri, researcher at the Welten Institute, studies how information captured real-time by wearable and contextual sensors can be used to predict learning performance. These sensors register for example head movements, gaze, vital signals (heart rate, skin conductance, EEG), posture, gestures, handwriting and spoken words. All these things separately contain very little information about what is happening in the learning process. (They have very low semantics.) However, combined and integrated with information about the learning context and activity they can provide meaningful information on the learning process and be used as input for automatically generated feedback and automatic formative assessment.

Machine learning

In his research Di Mitri captures multiple modalities of the learning process real-time through wearable and contextual sensors. By annotating these multimodal data (the input space) by expert assessments or self-reports (the output space), machine learning models can be trained to predict the learning performance. This can lead to continuous formative assessment and feedback generation, which can be used to personalise and contextualise content, improve awareness and support informed decisions about learning.

Di Mitri presented a paper about his research at the Artificial Intelligence in Education 2017 conference in Wuhan (China). This conference, co-located with the Educational Data Mining 2017 conference gathered top researchers in the field of data science in education. The paper is called 'Digital Learning Projection: Learning performance estimation from multimodal learning experiences.'

Laatst gewijzigd op: 10 jul 2017 9:40
Meer nieuwsberichten Aanmelden nieuwsbrieven