EAGER: Exploiting Keystroke Logging and Eye-Tracking to Support the Learning of Writing

PIs: Evgeny Chukharev-Khudilaynen, James Ranalli
Iowa State University
Award Details

Learning how to write and communicate well is one of the core challenges for becoming a productive member of society, and much is known about the psychology of the writing process. Yet, most writing instruction focuses instead on the product of writing, with limited ability to teach and support the moment to moment parts of writing, and only supporting the writing process after the fact. This project, an EAGER (EArly-concept Grant for Exploratory Research) explores the possibility that technology allowing the computer to tell where a writer is looking (reading), and what they are typing, can detect important aspects of their writing process and provide real-time feedback. Additionally, recording where learners look and what they type and allowing playback might support instructors of writing to teach some of the techniques that research shows can improve writing skills.

This project will prototype and test a scaffolded interactive online writing environment that synchronizes keystroke logging with eye-tracking gaze detection to enable automated detection of writing strategies. Through a co-development process including instructors of introductory college writing for primarily English as a Second Language learners and their students, the team will explore the pedagogical strategies that real-time analysis of eyetracking and keystroke logging enable, the constraints and affordances of using such technology in a classroom environment, and the types of formative feedback that have the greatest impact on writing strategies and outcomes. Initial phases of the research will validate that the software can accurately link gaze and keystrokes to an edit trace, and that the technology to do so can practically be disseminated in real classroom environments. The later phases of the research will focus on pedagogical strategies and their impacts; 14 focal students per semester will be recruited from the college level courses hosting the pilot, and these students will conduct a variety of writing tasks designed to elicit varied writing strategies; retrospective verbal protocols prompted by recordings of the technology use will be analyzed using macro-level coding conducted collaboratively by multiple researchers, and then subjected to both inductive and deductive qualitative analysis.