Implementing predictive learning analytics on a large scale

Herodotou, Christothea; Rienties, Bart; Boroowa, Avinash; Zdráhal, Zdeněk; Hlosta, Martin; Naydenova, Galina

doi:10.1145/3027385.3027397

Cited by 44 publications

(58 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through a mixed method study at a distance learning institution, Herodotou et al () found mixed effects on student's performance when 240 teachers in 10 modules were given access to PLA, yet usage analysis showed that teachers made only limited use of PLA in their practice that could explain these mixed effects. Five follow‐up interviews revealed that teachers had positive views about the use of PLA in teaching as they recognized their usefulness for complementing the teaching practice and being “on top of things.” Also, Herodotou, Rienties, Boroowa, Zdrahal, and Martin (n.d.) in a multi‐method study with 59 teachers and more than 1300 students identified that the teachers' overall engagement with predictive data was the second most significant factor explaining the student's performance, following the previous best performance.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…A wide body of literature suggests that predictive learning analytics (PLA) can help teachers and institutions in general, to overcome such challenges, by identifying which groups of students might need extra support to reach desired learning outcomes (Conijn, Snijders, Kleingeld, & Matzat, ; Haya et al , ; Herodotou et al , ; Kovanović et al , ; Scheffel et al , ). For example, Scheffel et al () found that visualizing the relative performance of 172 students using the PLA supported the learning processes over time.…”

Section: Introductionmentioning

confidence: 99%

“…Yet, Conijn et al () found that the PLA results varied substantially and concluded that virtual learning environment's (VLE's) engagement and clicking data are of limited value in the effective prediction of learning outcomes. Also, the PLA usage was shown to support teachers in identifying participation problems, facilitate regular interventions and complement existing teaching practices, yet the frequency of accessing PLA data varied and decreased over time, potentially affecting these outcomes (eg, Herodotou et al , ; van Leeuwen, Janssen, Erkens, & Brekelmans, , ) (see Section “Learning analytics and online teachers”).…”

Section: Introductionmentioning

confidence: 99%

“…In our quasi‐experimental design, we were particularly interested in exploring how the teachers' engagement with OUA relate to students' learning outcomes. In particular, building on existing insights showing a variation in the frequency of using the PLA and a decline usage of over time (eg, Herodotou et al , ; Dazo, Stepanek, Chauhan, & Dorn, ), we aimed to identify which usage patterns relate to better learning outcomes and how these patterns relate to non‐PLA‐related student's support approaches devised by teachers. This study answered the following research questions (RQs) as follows:

RQ1: How does teachers' usage of OUA relate to student's performance?RQ2: How does student's academic performance compares to peers in previous years' course presentation during which teachers made use of non‐PLA‐related student's support approaches?…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Empowering online teachers through predictive learning analytics

Herodotou¹,

Hlosta²,

Boroowa³

et al. 2019

Brit J Educational Tech

Self Cite

View full text Add to dashboard Cite

This study presents an advanced predictive learning analytics system, OU Analyse (OUA), and evidence from its evaluation with online teachers at a distance learning university. OUA is a predictive system that uses machine learning methods for the early identification of students at risk of not submitting (or failing) their next assignment. Teachers have access, via interactive dashboards, to weekly predictions of risk of failing for each of their students. In this study, we examined how the degree of OUA usage by 559 teachers, of which 189 were given access to OUA, related to student learning outcomes of more than 14 000 students in 15 undergraduate courses. Teachers who made “average” use of OUA, that is accessed OUA throughout the life cycle of a course presentation, and in particular between 10% and 40% of the weeks a course was running, and intervened with students flagged as at risk were found to benefit their students the most; after controlling for differences in academic performance, these students were found to have significantly better performance than their peers in the previous year's course presentation during which the same teachers made no use of predictive learning analytics. Predictive learning analytics is an innovative student's support approach in online pedagogy that, as shown in this study, can empower online teachers in effectively monitoring and intervening with their students, over and above other approaches, and result in improved learning outcomes. What is already known about this topic Pedagogical and personal support to students is a significant responsibility of online teachers. Student's support is a challenging activity due to the lack of face‐to‐face interactions. Predictive learning analytics (PLA) can identify students at risk of failing their studies. What this paper adds One of the few large‐scale studies is available for examining the impact of analytics on student's performance. Teachers' usage of PLA was significantly related to better learning outcomes. Online teachers had students with better learning outcomes when accessing PLA data rather than when they had no access. Implications for practice and/or policy PLA can empower online teachers and complement the teaching practice. PLA can help in the identification and proactive intervention of students at risk of failing their studies. Actions should be taken to motivate and engage online teachers with PLA.

show abstract

Section: Theoretical Backgroundmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Empowering online teachers through predictive learning analytics

Herodotou¹,

Hlosta²,

Boroowa³

et al. 2019

Brit J Educational Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…A recent study by Herodotou et al (2017) tested the actual use of predictive LA data by 240 teachers at the OU-UK in 10 distance learning modules and found that teachers reacted in diverse ways to the availability of predictions flagging students at risk. Most of them engaged irregularly and infrequently with the predictive data and many struggled to find ways to undertake interventions and provide support to students.…”

Section: Challenges To Using La In Callmentioning

confidence: 99%

Affordances and limitations of learning analytics for computer-assisted language learning: a case study of the VITAL project

Gelan

Fastré

Verjans

et al. 2018

Computer Assisted Language Learning

View full text Add to dashboard Cite

Learning analytics (LA) has emerged as a field that offers promising new ways to support failing or weaker students, prevent drop-out and aid retention. However, other research suggests that large datasets of learner activity can be used to understand online learning behaviour and improve pedagogy. While the use of LA in language learning has received little attention to date, available research suggests that understanding language learner behaviour could provide valuable insights into task design for instructors and materials designers, as well as help students with effective learning strategies and personalised learning pathways. This paper first discusses previous research in the field of language learning and teaching based on learner tracking and the specific affordances of LA for CALL, as well as its inherent limitations and challenges. The second part of the paper analyses data arising from the European Commission (EC) funded VITAL project that adopted a bottom-up pedagogical approach to LA and implemented learner activity tracking in different blended or distance learning settings.Referring to data arising from 285 undergraduate students on a Business French course at Hasselt University which used a flipped classroom design, statistical and process-mining techniques were applied to map and visualise actual uses of online learning resources over the course of one semester.Results suggested that most students planned their self-study sessions in accordance with the flipped classroom design, both in terms of their timing of online activity and selection of contents. Other metrics measuring active online engagement -a crucial component of

show abstract