Towards Next Generation Rubrics: An Automated Assignment Feedback System


  • Nilupulee Nathawitharana La Trobe University
  • Qing Huang La Trobe University
  • Kok-Leong Ong La Trobe University
  • Peter Vitartas La Trobe University
  • Madhura Jayaratne La Trobe University
  • Damminda Alahakoon La Trobe University
  • Sarah Midford La Trobe University
  • Aleks Michalewicz La Trobe University
  • Gillian Sullivan Mort La Trobe University
  • Tanvir Ahmed La Trobe University



Learning analytics, Automated Writing Evaluation, Text analysis, Assignment feedback


As the use of blended learning environments and digital technologies become integrated into the higher education sector, rich technologies such as analytics have shown promise in facilitating teaching and learning. One popular application of analytics is Automated Writing Evaluation (AWE) systems. Such systems can be used in a formative way; for example, by providing students with feedback on digitally submitted assignments. This paper presents work on the development of an AWE software tool for an Australian university using advanced text analytics techniques. The tool was designed to provide students with timely feedback on their initial assignment drafts, for revision and further improvement. Moreover, it could also assist academics in better understanding students’ assignment performance so as to inform future teaching activities. The paper provides details on the methodology used for development of the software, and presents the results obtained from the analysis of text-based assignments submitted in two subjects. The results are discussed, highlighting how the tool can provide practical value, followed by insights into existing challenges and possible future directions.




How to Cite

Nathawitharana, N., Huang, Q., Ong, K.-L., Vitartas, P., Jayaratne, M., Alahakoon, D., Midford, S., Michalewicz, A., Sullivan Mort, G., & Ahmed, T. (2017). Towards Next Generation Rubrics: An Automated Assignment Feedback System. Australasian Journal of Information Systems, 21.



Selected Papers from the Australasian Conference on Data Mining (AusDM)