FOUNDATIONS OF DYNAMIC LEARNING ANALYTICS: USING UNIVERSITY STUDENT DATA TO INCREASE RETENTION (pre publication draft). De Freitas, S.; Gibson, D.; Rogers, M.; Plessis, C., D.; Halloran, P.; Dunwell, I.; Downie, J.; and Arnab, S. Technical Report
abstract   bibtex   
Today, a plethora of data sets can be harvested from digital learning experiences, learning management systems and the entire digital student life, which store learning content and track user behaviours. As a result, educators have access to very large and detailed datasets that open the entire student experience to greater scrutiny and analysis. Most recently, learning analytics approaches are creating new ways of understanding trends in student behaviours that can be used to improve learning design, strengthen student retention and provide early warning signals concerning individual students that can help to personalise the learner's experience in new ways and to new levels of detail. This paper summarises lessons learnt from a learning analytics project at Curtin University in Western Australia, and proposes a dynamic learning analytics model (DLA) for higher education that goes beyond descriptive and predictive analytics reports created by experts. The model focuses on the dynamic interaction of stakeholders with their data in analytical processes supported by visualization and machine learning approaches such as self-organizing maps, to generate conversations and stimulate shared inquiry and solution-seeking. The findings from the study can be applied to help shape how educational institutions design learning analytics processes to support innovations in personalized learning and support services and achieve both higher rates of, and smarter student retention through more highly targeted recruitment, learning opportunities and services.
@techreport{
 title = {FOUNDATIONS OF DYNAMIC LEARNING ANALYTICS: USING UNIVERSITY STUDENT DATA TO INCREASE RETENTION (pre publication draft)},
 type = {techreport},
 id = {f694c4fa-930c-3391-b6d1-e92300311d34},
 created = {2020-02-03T14:13:30.869Z},
 accessed = {2020-02-03},
 file_attached = {false},
 profile_id = {bfdabac2-d7f2-3c5b-aa7a-06431c0ae35e},
 group_id = {ed1fa25d-c56b-3067-962d-9d08ff49394c},
 last_modified = {2020-02-03T14:13:31.262Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 folder_uuids = {af1b8628-85f8-4733-9f52-121159400517},
 private_publication = {false},
 abstract = {Today, a plethora of data sets can be harvested from digital learning experiences, learning management systems and the entire digital student life, which store learning content and track user behaviours. As a result, educators have access to very large and detailed datasets that open the entire student experience to greater scrutiny and analysis. Most recently, learning analytics approaches are creating new ways of understanding trends in student behaviours that can be used to improve learning design, strengthen student retention and provide early warning signals concerning individual students that can help to personalise the learner's experience in new ways and to new levels of detail. This paper summarises lessons learnt from a learning analytics project at Curtin University in Western Australia, and proposes a dynamic learning analytics model (DLA) for higher education that goes beyond descriptive and predictive analytics reports created by experts. The model focuses on the dynamic interaction of stakeholders with their data in analytical processes supported by visualization and machine learning approaches such as self-organizing maps, to generate conversations and stimulate shared inquiry and solution-seeking. The findings from the study can be applied to help shape how educational institutions design learning analytics processes to support innovations in personalized learning and support services and achieve both higher rates of, and smarter student retention through more highly targeted recruitment, learning opportunities and services.},
 bibtype = {techreport},
 author = {De Freitas, Sara and Gibson, David and Rogers, Michelle and Plessis, Coert Du and Halloran, Pat and Dunwell, Ian and Downie, Jill and Arnab, Sylvester}
}
Downloads: 0