Real-time AI-mediated peer feedback in L2 writing: a mixed-methods study of learner engagement and accuracy development

Peer feedback has been of paramount importance in second language (L2) writing given that L2 learners especially need the facilitative role of feedback in improving their writing skills. Despite recent research highlighting the benefits of peer feedback in L2 writing, there is a call for more qualitative studies situated in classroom contexts to explore the continuous flow of peer feedback in a social community including technology-enhanced interactive social settings. This case study takes the students at a university in Turkey as the center of the peer feedback process and explores how L2 writers (n = 35) using student blogs for online peer evaluation in the naturalistic setting of an academic writing course perceive online peer feedback in L2 writing. This qualitative study adopted a case study design using the data from students’ essays (210 essays), blog-mediated peer comments (on 35 student blogs), and self-reflection papers (105 reflections). The data was analyzed through Braun and Clarke’s inductive thematic analysis. The analysis resulting in four themes revealed that peer feedback experienced in an online writing community improved students’ ability to perceive and use feedback effectively by creating opportunities for a shared understanding of peer feedback and establishing a writing community and also enhanced students’ critical thinking skills as an essential aspect of the writing process. This study provides insights into the student experience of online peer feedback in L2 writing, highlighting the importance of creating a supportive and collaborative learning environment to foster effective feedback practices and enhance the students’ L2 writing skills.

Student engagement with peer feedback in L2 writing: Insights from reflective journaling and revising practices

This article reviews research on peer feedback in second language (L2) writing published in the last decade (i.e. 2005–2014). We analyse first the theoretical underpinnings that have informed both peer feedback research and the pedagogical use of peer feedback in L2 writing instruction. We also provide a critical interpretation of existing peer feedback research and discuss seven important themes emerging from the literature, that is, (1) effectiveness of peer feedback compared with teacher and self-feedback; (2) benefits of peer feedback for feedback-givers; (3) computer-mediated peer feedback; (4) peer feedback training; (5) student stances and motives; (6) peer interaction and group dynamics; and (7) cultural issues in peer feedback. Next, we examine the contextual and methodological issues in peer feedback research and then conclude the article with implications for future research.

While the past few decades have witnessed a growing body of research on peer feedback and student engagement, little attention has been paid to student engagement with peer feedback in the secondary school classrooms. Based on multiple qualitative data including semi-structured interviews, stimulated recall, original, revised and final writing drafts as well as peer discussion recordings, this case study investigated how secondary school students engaged with peer feedback in behavior, cognition, and affect from both the feedback giver’s and receiver’s perspectives and what factors may influence their engagement with peer feedback. Data analysis showed that 1) student engagement with both giving and receiving peer feedback demonstrated dynamic and complex interactions among three dimensions; 2) students were engaged with peer feedback in different ways while playing the roles of feedback givers and receivers, showing deep engagement as a giver and superficial engagement as a receiver, and vice versa; 3) factors such as language proficiency, self-efficacy, personality and teachers’ guidance were found to influence student engagement with peer feedback. By shedding light on the multi-dimensional characteristics of students’ engagement from bidirectional perspectives, the study offers suggestions for educational practitioners to improve English learners’ engagement with peer feedback in L2 writing classes.

The study aims to undertake an investigation regarding the different effect of teacher vs. peer feedback on varied sections of writing proficiency among secondary students in Bologna, Italy. The research employed a structured questionnaire to a sample of 150 students in an inquiry that sought to establish the effectiveness of these feedback modalities in enhancing writing tasks. The analysis was also supported by SPSS, which helped in reaching a comprehensive understanding of the dynamics within feedback. The results provide a much more nuanced picture in which peer feedback, under certain conditions, actually has the potential to be as effective as traditional teacher feedback in facilitating writing development. More specifically, the peer feedback resulted in substantially improving the content, organization, and vocabulary to the same degree as teacher feedback, with the lone exception of grammar increase. The results point toward a peer-feedback experience that is a potentially valid addition to teacher-led revisions, provided initiatives to integrate it with feedback literacy are focused on putting student empowerment at their core. The research has therefore added to the broader discussion of feedback mechanisms in language learning by proposing a re-evaluation of the nature of peer feedback within educational paradigms.

ABSTRACTDue to advances in natural language processing and artificial intelligence, automated feedback, teacher feedback, and peer feedback have been available for teachers to utilize in their L2 writing classrooms. Integrating these kinds of feedback in L2 writing instruction remains challenging. This study aimed to explore the way to integrate teacher feedback, peer feedback, and automated feedback into various writing tasks in L2 writing classrooms by combining teachers' and students' perspectives. Based on a survey of 286 tertiary EFL students and 65 teachers engaging in the writing classrooms, this study revealed that (1) teachers and students showed similarities and differences in their judgment of the complexity of writing tasks involved in L2 classrooms; (2) differences were found between students and teachers in the feedback preference for these tasks; and (3) teachers' feedback preference showed strong correlations with their judgment of the complexity of the writing tasks, whereas no such correlations were found among students.

The present case study aims to revisit the role of Chinese traditional cultural issues in group peer feedback by examining how Chinese EFL students respond to several typical Chinese cultural issues that have emerged from the literature—“collectivism and group harmony,” “face-saving,” and “power distance” and what factors have shaped their beliefs and practices regarding these cultural issues. Multiple sources of data were collected, including video recordings of peer feedback sessions, interviews, and stimulated recalls. The findings show that while there were individual differences in the four students’ beliefs and practices with regard to the cultural issues, on the whole the cultural issues did not constrain their group peer feedback activity. The study also found that the students’ beliefs and practices were embedded in a number of interrelating individual and contextual factors like the Chinese cultures of learning, the group context, and the students’ previous feedback experience. This study cast doubt on previous research that suggests the traditional Chinese cultural issues constrained the implementation of peer feedback activity and marred the effectiveness of peer feedback in L2 writing.

The present mixed-method study examined the foci and effects of peer and machine feedback on the revisions of Chinese university EFL learners’ English argumentative essays. The data included Draft 1, peer feedback (PF), PF-based Draft 2, machine feedback (MF), MF-based feedback, questionnaires, and interview recordings. The main findings were: (a) peer feedback was primarily concerned with content errors, while machine feedback mainly involved non-content errors, (b) significant differences occurred in errors of most types between Draft 1, PF and PF-based Draft 2, and between Draft 1, MF, and MF-based Draft 2, (c) the intake of ‘introducing a new topic in Conclusion’ was a powerful predictor of PF-based Draft 2 scores, and (d) the participants generally moderately considered peer and machine feedback to be useful. Based on the findings, some implications are discussed on how to better implement and enhance the quality of peer and machine feedback.

As a vital learning activity in second language (L2) writing classrooms, peer feedback plays a crucial role in improving students' writing skills. However, student reviewers face challenges in providing impactful feedback on peers' essays. Low‐quality peer reviews emerge as a persistent problem, adversely affecting the learning effect of peer feedback. To enhance students' peer feedback provision, this study introduces EvaluMate, an AI‐supported peer review system, which incorporates a chatbot named Eva, designed to evaluate and provide feedback on student reviewers' comments on peers' essays. Forty‐four Chinese undergraduate students engaged with EvaluMate, utilising its features to generate feedback on peers' English argumentative essays. Chat log data capturing the students' interactions with the chatbot were collected, including the comments they wrote on peer essays and the feedback offered by the chatbot on their comments. The results indicate that the integration of AI supervision improved the quality of students' peer reviews. Students employed various strategies during their comment revision in response to AI feedback, such as introducing new points, adding details, and providing illustrative examples, which helped improve their comment quality. These findings shed light on the benefits of AI‐supported peer review systems in empowering students to provide more valuable feedback on peers' written work. Practitioner notes What is already known about this topic Scholars have extensively investigated diverse pedagogical strategies to enhance students' peer feedback provision skills in second language (L2) writing classrooms. Artificial intelligence (AI) technologies have been utilised to monitor and evaluate the peer feedback generated by student reviewers. AI‐enabled peer feedback evaluation tools have demonstrated the ability to provide valid assessments of student reviewers' peer feedback. What this paper adds In the context of L2 writing, there is a lack of bespoke AI‐enabled peer feedback evaluation tools. To address this gap, we have developed an AI‐supported peer review system, EvaluMate, which incorporates a large language model‐based chatbot named Eva. Eva is designed to provide feedback on L2 students' comments on their peers' writing. While previous studies have primarily focused on assessing the validity of AI‐enabled peer feedback evaluation tools, little is known about how students incorporate AI support into improving their peer review comments. To bridge this gap, our study examines not only whether using the system (EvaluMate) can enhance the quality of L2 students' peer review comments but also how students respond to Eva's feedback when revising their comments. Implications for practice and/or policy The development of the AI‐supported peer review system (EvaluMate) introduces an innovative pedagogical approach for L2 writing teachers to train and enhance their students' peer feedback provision skills. Integrating AI supervision into L2 students' peer feedback generation improves the quality of comments provided by student reviewers on their peers' writing. Students employ various strategies when revising their comments in response to Eva's feedback, and these strategies result in varying degrees of improvement in comment quality. L2 writing teachers can teach effective revision strategies to their students.

Understanding student engagement with teacher and peer feedback in L2 writing

ABSTRACTThe present study examined the impact of trained peer feedback on Spanish as a second language (L2) in terms of language performance, nature of feedback, and perceptions of peer feedback in speaking tasks. Participants in the study included 17 intermediate L2 Spanish learners enrolled in a conversation course that incorporated peer feedback practices in a multiple draft-based approach to practice L2 speaking. Pre-intervention questionnaires, various drafts of learner speech samples, peers’ written feedback, and post-intervention questionnaires were administered and analyzed. Although significant differences were not found in language performance across multiple speaking drafts, learners reported a positive learning value from the speaking multi-draft approach, which encouraged them to listen to their peers’ speech samples and provide feedback. Moreover, the results show that learners provided affective types of feedback and ventured to contribute comments regarding language accuracy. The present study confirms previous findings about the value of peer feedback in L2 writing, all be it in a new context, speaking. The researchers attest to the learning value of the process approach in speaking, training interventions, and peer feedback, as they positively impact learners’ self-efficacy in speaking.

Cho, Yunkyoung & Sohn, Taeho. (2007). Complementarity of peer and teacher feedback in Korean high school English classes. English Teaching, 62(3), 307-329. The present study is interested in examining the issue of complementarity of peer feedback and teacher feedback as employed in Korean secondary English classes. Specifically, the complementarity of the two feedback sources was examined in three respects: the nature of feedback, the incorporation of feedback into revision, and the effects of feedback on the improvement of the revised drafts. The overall findings seem to support the complementarity of the two types of feedback. First, teacher feedback was predominantly concerned with the surface level of writing, while some of the peer feedback concerned content and organization. Second, almost all of the teacher feedback was accepted or adapted in revision, while the students in the peer feedback group were selective in choosing which peer feedback to use in revisions. Lastly, the quality of the second drafts of the two groups did not significantly differ, and both the teacher and peer feedback were found to be effective in promoting revisions. Despite a few methodological limitations, these findings indicate that Korean EFL secondary learners could benefit from peer feedback in different ways from teacher feedback.

The recent two decades have witnessed a greater interest in L2 writing research to explore how individual learners engage with and participate in peer feedback. However, not much attention has been directed to peer feedback in the collaborative format, despite the fact that peer collaboration can enable learners to draw on their respective strengths and pool their knowledge. In this qualitative study, we adopted an educational psychological perspective to discover the intricate nature of learners working together to give anonymous feedback to their peers. In addition to learners' cognitive engagement with the correction and revision process, we also investigated learners' affective, behavioral, and social engagement in collaborative peer feedback. The findings show that, although learners can cognitively engage with the task by identifying a number of language-related problems and providing feedback, their affective, behavioral, and social engagement differed considerably. While some participants' engagement was relatively extensive, especially in the affective and social aspect, others' engagement was at a relatively limited level, characterized by negative emotions and low mutuality in peer interaction. The unpleasant task experience affected their attitudes toward collaborative peer feedback activities and their willingness to participate in subsequent tasks.

Engaging in dialogic peer feedback in L2 writing development: A microgenetic approach

Using data from a qualitative study into the effects of feedback on ESL writers, this paper looks at the peer and teacher feedback offered to individual writers. The paper suggests that teachers sometimes also override student concerns and decisions on use of feedback, even when peer feedback, which appears to allow for more student participation in the feedback process is involved. It focuses on the cases of two students, whose use of feedback and interactions with their teachers raise questions relating to the ownership of their writing and revision processes. It is sugggested that teacher interventions may lead to students relinquishing control of their writing and revision processes, as well as their written products. The paper suggests that in some circumstances, teachers should encourage students to take more responsibility for their own writing, by allowing them to make their own decisions about their use and sources of feedback.