Download PDFOpen PDF in browser

Predicting Academic Achievement With Students' Learning Diary and Epistemic Beliefs

10 pagesPublished: September 20, 2022

Abstract

Epistemic cognition has been found to positively predict academic achievement. However, measuring epistemic cognition has proved to be problematic. In the last decade, learning analytics has emerged as a field of study and practice with new means to collect data on different types of psychological constructs.
This study focuses on a learning analytics tool, a structured learning diary, and its connections with self-reported epistemic beliefs. Connections between these and academic achievement are investigated at four temporal measurement points. The first aim was to test which measures of the diary tool correlated with academic achievement. The second aim was to test epistemic beliefs' correlation with academic achievement. Models of linear regression were then designed and tested at different times.
The results show that we should collect student-originated behaviour data for the best predictive power and connect that with independent psychological measures.

Keyphrases: academic achievement, education, epistemic beliefs, linear multiple regression, predictive models, structured learning diary

In: Jean-François Desnos, Ramin Yahyapour and Raimund Vogl (editors). Proceedings of EUNIS 2022 – The 28th International Congress of European University Information Systems, vol 86, pages 168-177.

BibTeX entry
@inproceedings{EUNIS2022:Predicting_Academic_Achievement_With,
  author    = {Ville Kivimäki},
  title     = {Predicting Academic Achievement With Students' Learning Diary and Epistemic Beliefs},
  booktitle = {Proceedings of EUNIS 2022 –  The 28th International Congress of European University Information Systems},
  editor    = {Jean-François Desnos and Ramin Yahyapour and Raimund Vogl},
  series    = {EPiC Series in Computing},
  volume    = {86},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/MgLN},
  doi       = {10.29007/zzfc},
  pages     = {168-177},
  year      = {2022}}
Download PDFOpen PDF in browser