Edited By Dagmar Knorr, Carmen Heine and Jan Engberg
Applying machine learning techniques to investigate the influence of peer feedback on the writing process
Despite teachers including peer feedback as a tool to support writer’s development, it is only in the last few years that considerable progress has been made in gaining a better understanding of how, when, and whether peer feedback positively influences the writing process. It has been the introduction of web-based peer review systems that is currently making a considerable impact. This paper elaborates how web-based reciprocal peer review systems can be used to collect large amounts of authentic student generated data (e. g. feedback on writing, revision carried out on drafts), and how the data science methods collectively known as machine learning can be used to analyse this data to provide more insight into the writing process.
It is now generally accepted in writing process research that revision is one of the key components of writing in general, and of learning to write in particular. Ever since Flower and Hayes (1981) presented their writing process model, there has been a steady stream of research on the impact of revision on learning to write. Although Flower and Hayes recognized differences among frequent writers and learners of writing, they were nonetheless able to propose the general hypothesis that revision is done, regardless who carries it out, either throughout the process of writing sentences forming the text, or after the text has been generally constructed (Becker 2006). Given that revision is invaluable, from a pedagogical perspective, and has a special application in the writing process (Hayes 2012), it is also recognized...
You are not authenticated to view the full text of this chapter or article.
This site requires a subscription or purchase to access the full text of books or journals.
Do you have any questions? Contact us.Or login to access all content.