Collaborating with Mature English Language Learners to Combine Peer and Automated Feedback: a User-Centered Approach to Designing Writing Support

Abstract

300,000 immigrants move to Canada each year in search of better economic opportunities, and many have limited English language skills. Improving written literacy of newcomers can enhance education, employment, or social integration opportunities. However, frequent, timely, and personalized feedback is not always possible for immigrants. Online writing support tools can scaffold writing development by providing this feedback, but existing systems provide inadequate support when instructors are inaccessible. In this paper, we show how feedback system design can leverage peer and automated feedback to support mature English Language Learners’ (ELL) needs and practices. We identify strong associations between epistemic beliefs and learning strategies, highlighting the importance of tasks that activate productive epistemic beliefs. We find learners accurately assessed high-level issues in a peer’s writing and are accepting of automated feedback, demonstrating that a platform combining peer-review and machine feedback could promote meaningful discussions. We present the results of our mixed-methods investigation that integrates three sources of information: analysis of learners’ psychometric constructs, writing samples to identify error patterns, and participatory design group sessions incorporating human-centred design methods. We synthesize our results into four guidelines derived from seven findings resulting from the investigation of a system that scaffolds writing development for mature immigrant ELLs in the absence of formal instructional support. First, we find that ELLs require a platform to collaboratively iterate through the writing process. Next, we suggest how peer feedback can be enhanced through automated support. We then demonstrate how rubric design can guide both linear and holistic peer-review. Finally, we illustrate why open learner models and learning dashboards should contextualize real world progress.