A review of learning analytics intervention in higher education (2011–2018)

Intervention has long been practised in higher education to provide assistance for at-risk or underachieving learners. With the development of learning analytics, the delivery of intervention has been informed by data-driven approaches to identify learners’ problems and provide them with just-in-time and personalised support. However, intervention has been claimed to be the greatest challenge in learning analytics and has yet to be widely implemented. This paper reviews 24 case studies of learning analytics intervention in higher education. The cases were categorised and summarised according to their objectives, the data used, the intervention methods, the outcomes obtained and the challenges encountered. The results show that intervention practices have focused most frequently on increasing students’ study performance, offering personalised feedback and improving student retention. The frequent types of data involved students’ online learning behaviours, study performance, demographics and course selection information. The most commonly used intervention methods involved offering personalised recommendations and visualising learning data. The interventions have led to outcomes such as enhancing study performance, retention and course registration, as well as productivity and effectiveness in learning and teaching. The challenges covered a wide range of aspects, including the scalability of intervention, conditions for implementing intervention, limitations of the channels for delivering intervention and the evaluation of intervention effectiveness. The results suggest that learning analytics intervention has the potential to further extend its scope of practices to serve a wider range of purposes, but more studies on the empirical evidence, even with null or negative results, are needed to support its long-term effectiveness and sustainability.