SR-WMS: A Typology of Self-Regulation in Writing from Multiple Sources

Raković, Mladen; Winne, Philip H.

doi:10.1007/978-3-031-06333-6_7

Cited by 2 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The systems for automated evaluation of multi‐text writing developed to date have mainly assessed linguistic characteristics of a written product to inform product‐oriented formative feedback and help learners succeed in this demanding task. Abundant self‐regulated learning processes that learners consciously engage in while working on this task (Raković & Winne, 2022) have been rarely studied to inform process‐oriented feedback in multi‐text writing. As both product‐ and process‐oriented feedback are essential to boost learner performance in writing tasks (Durako et al, 1996; Schunk & Swartz, 1993), in the present study we explored the viability of using product and process features to develop machine learning classifiers to predict learner performance, and then reveal SRL processes and characteristics of an essay product that influence performance in an authentic multi‐text writing task.…”

Section: Discussionmentioning

confidence: 99%

“…While developing their written compositions, multi‐text writers alternate between textual documents and essay draft. They engage in multiple cognitive and metacognitive processes to support their reading comprehension and writing production (Raković et al, 2019; Raković & Winne, 2022). To manage, monitor and capitalize on these processes, and develop effective written compositions that fulfil task requirements, multi‐text writers need to engage in extensive and productive self‐regulation (Raković & Winne, 2022), i.e., they need to self‐regulate their reading and writing processes.…”

Section: Related Workmentioning

confidence: 99%

“…They engage in multiple cognitive and metacognitive processes to support their reading comprehension and writing production (Raković et al, 2019; Raković & Winne, 2022). To manage, monitor and capitalize on these processes, and develop effective written compositions that fulfil task requirements, multi‐text writers need to engage in extensive and productive self‐regulation (Raković & Winne, 2022), i.e., they need to self‐regulate their reading and writing processes. According to Winne and Hadwin (1998), SRL encompasses multiple cognitive and metacognitive processes that unfold over four loosely ordered stages: task definition, goal setting and planning, strategy enactment and adaptation.…”

Section: Related Workmentioning

confidence: 99%

“…In these assignments, educators create opportunities for learners to hone their reading and writing skills by comprehending information from multiple textual documents and integrating this information into a written composition of a particular genre (Rouet et al, 1996; Spivey & King, 1989), for example, argumentative essay, research synthesis and lab report. Even though educationally promising (Mateos et al, 2014; Tynjälä, 2001), multi‐text writing has been considered a demanding task (Allen et al, 2016; De La Paz & Felton, 2010), as learners working on this task need to alternate between texts provided and essay draft, and engage a myriad of cognitive and metacognitive processes that this task demands, for example, read, take notes, elaborate and monitor whether the evolving essay draft aligns with task requirements (Cho et al, 2018; Raković & Winne, 2022; Winne, 2021; Winne & Hadwin, 1998). To fully benefit from multi‐text writing tasks, learners need to strategically invoke these processes during the writing session (Britt & Rouet, 2012), i.e., they need to engage in productive self‐regulated learning (SRL).…”

Section: Introductionmentioning

confidence: 99%

“…To overcome the existing challenges and facilitate formative assessment in multi‐text writing, researchers have proposed several systems for automatic writing evaluation based on machine learning (ML) and natural language processing (NLP) approaches. These systems have demonstrated a potential to provide at‐scale insight into different elements of an essay draft that affect quality and score of a multi‐text essay, for example, explanation (Hughes et al, 2015; Wiley et al, 2017), coverage of source topics (Hastings et al, 2012), and use of evidence (Raković & Winne, 2022; Zhang et al, 2019). These systems have mainly relied upon product features, i.e., linguistic features derived from the essay text.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Harnessing the potential of trace data and linguistic analysis to predict learner performance in a multi‐text writing task

Raković

Iqbal

et al. 2022

Computer Assisted Learning

View full text Add to dashboard Cite

Background: Assignments that involve writing based on several texts are challenging to many learners. Formative feedback supporting learners in these tasks should be informed by the characteristics of evolving written product and by the characteristics of learning processes learners enacted while developing the product. However, formative feedback in writing tasks based on multiple texts has almost exclusively focused on essay product and rarely included SRL processes.Objectives: We explored the viability of using product and process features to develop machine learning classifiers that identify low-and high-performing essays in a multi-text writing task.Methods: We examined learning processes and essay submissions of 163 graduate students working on an authentic multi-text writing assignment. We utilised learners' trace data to obtain process features and state-of-the-art natural language processing methods to obtain product features for our classifiers. Results and Conclusions: Of four popular classifiers examined in this study, RandomForest achieved the best performance (accuracy = 0.80 and recall = 0.77). The analysis of important features identified in the Random Forest classification model revealed one product (coverage of reading topics) and three process (elaboration/organisation, rereading and planning) features as important predictors of writing quality.Major Takeaways: The classifier can be used as a part of a future automated writing evaluation system that will support at scale formative assessment in writing tasks based on multiple texts in different courses. Based on important predictors of essay performance, a guidance can be tailored to learners at the outset of a multi-text writing task to help them do well in the task.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Harnessing the potential of trace data and linguistic analysis to predict learner performance in a multi‐text writing task

Raković

Iqbal

et al. 2022

Computer Assisted Learning

View full text Add to dashboard Cite

show abstract

Secondary School Students’ Enacted Self-Regulated Learning Strategies in a Computer-Based Writing Task–Insights from Digital Trace Data and Interviews

Aksela,

Lämsä,

Järvelä

2024

Tech Know Learn

View full text Add to dashboard Cite

Studying in digital learning environments highlights the skills needed to regulate one’s own learning. In youth, students are acquiring and developing these skills, but for many students, effectively self-regulating their learning is challenging. To design support in this regard, an in depth understanding of how and why their self-regulated learning (SRL) is enacted is needed. This study focuses on secondary school students’ enacted SRL strategies in a computer-based, multi-source writing task to detect and explain differences between high- and low-performing students. To address this aim, the students’ SRL processes during the task were captured using digital trace data (N = 50, navigational log, mouse, and keyboard data) and supplemented with stimulated recall interviews (n = 17). Raw trace data were parsed by implementing an existing theory-based process library that automatically detects the SRL processes. The durations and network properties of and transitions between the SRL processes of students in the highest and lowest essay score tertiles were investigated, involving the novel application of network metrics, and a qualitative content analysis for the stimulated recall data was performed. The results show that successful students differed from less successful ones regarding the time they allotted for the SRL processes, the number of distinct transitions between them, as well as transition probabilities. The successful students expressed a larger proportion of and different cyclical patterns of SRL processes during the task. The student interviews contextualise these findings and complement them by revealing qualitative differences in students’ monitoring of learning. This study provides novel insights into SRL among young students in computer-based writing task and suggests approaches for designing effective, personalised support for students’ adaptive learning strategies, which can be useful in developing educational technology and teacher education.

show abstract

SR-WMS: A Typology of Self-Regulation in Writing from Multiple Sources

Cited by 2 publications

References 37 publications

Harnessing the potential of trace data and linguistic analysis to predict learner performance in a multi‐text writing task

Harnessing the potential of trace data and linguistic analysis to predict learner performance in a multi‐text writing task

Secondary School Students’ Enacted Self-Regulated Learning Strategies in a Computer-Based Writing Task–Insights from Digital Trace Data and Interviews

Contact Info

Product

Resources

About