Emily Dux Speltz, Ph.D.
Research
Specific Research Interests:
— Process-focused writing instruction
— Writing center feedback
— Artificial intelligence for writing and learning
— Writing and educational technologies
— Applied psycholinguistics
Research Methods:
— Eye tracking
— Keystroke logging
— Natural language processing
— Design-based research
— Thematic analysis
— Cluster analysis
— Qualitative methods (case studies, interviews, focus groups)
Recently funded by the NSF: Conference on text production and comprehension by human and artificial intelligence
Abstract: The ability to read and write effectively is crucial for learning, communication, and creating knowledge across all fields. However, there is still much to understand about how people cognitively process written language and how emerging artificial intelligence technologies could interact with these human capabilities. This workshop brought together experts from cognitive psychology, language learning, and natural language processing with artificial intelligence. By combining insights across these disciplines, the workshop aimed to unlock new understanding about how people produce and mentally represent written language knowledge, as well as how large language models could potentially enhance reading and writing abilities. This cross-disciplinary collaboration could lead to more effective education approaches, innovative learning technologies, and guidelines for ethically integrating artificial intelligence with human skills involving written text.

The workshop convened a group of experts who share their latest research on how humans and artificial intelligence systems comprehend and generate written language. Participants discussed their findings, identified key challenges, explored possible solutions, and mapped future research directions. Through dialogue between the cognitive, linguistic, and technological perspectives, researchers examined the underlying cognitive processes when humans and artificial intelligence collaborate on text-based tasks. They investigated the potential for artificial intelligence language models to support the development of reading and writing skills and personalized learning experiences. This project allowed participants to further understand the interaction between human cognition and artificial intelligence when engaging with written texts across educational and professional settings.

Link to NSF award summary.
Link to workshop website
Highlighted Publications
Automating individualized, process-focused writing instruction: A design-based research study
Emily Dux Speltz, Jens Roeser, & Evgeny Chukharev
Frontiers in Communication
Writing quality is dependent upon the organization and sequencing of cognitive processes during writing. College students need writing-strategy advice that is tailored to their individual needs and is cognizant of their already-established writing processes. However, there is an obstacle to providing such advice: Both writing instructors and the writers lack awareness of the moment-by-moment actions by which text was produced. This is because switching between the processes of defining the task, coming up with ideas, outputting text, evaluating, and revising is largely regulated implicitly.
To address this shortcoming, the present study uses a design-based research approach to develop and evaluate a minimally viable prototype of a system called “ProWrite” that uses novel biometric technology (concurrent keystroke logging and eye tracking) for providing real-time, individualized, automated, process-focused feedback to writers. This feedback is grounded in the analysis of each writer's individual needs and is presented in the context of a learning cycle consisting of an initial diagnostic, an intervention assignment, and a final follow-up. In two iterations, eight students used the system. Effects on student behavior were determined through direct analysis of biometric writing-process data before and after remediation and through changes in writing-process and written-product measures. Semi-structured interviews revealed that students generally considered the system useful, and they would try to use the newly learned strategies in their future writing experiences. The study demonstrated that individualized, real-time feedback informed by biometric technology can effectively modify writers' processes when writing takes place.

The effect of automated fluency-focused feedback on text production
Emily Dux Speltz & Evgeny Chukharev
Journal of Writing Research
This article presents a new intervention for improving first-language writing fluency and reports an empirical study investigating the effects of this intervention on process and product measures of writing. The intervention explicitly encourages fluent text production by providing automated real-time feedback to the writer.
Participants were twenty native-English-speaking undergraduate students at a large Midwestern university in the United States, all of whom were proficient writers. Each participant composed two texts (one in each of the control and the intervention condition) in an online text editor with embedded keystroke logging capabilities. Quantitative data consisted of product and process measures obtained from texts produced by participants in the control and the intervention condition, and qualitative data included participants' responses to an open-ended questionnaire. Linear mixed-effects regression models were fit to the quantitative data to assess differences between conditions. Findings demonstrated that there were significant differences between the intervention and the control condition in terms of both the product and the process of writing. Specifically, participants wrote more text, expressed more ideas, and produced higher-quality texts in the fluency-focused intervention condition. Qualitative findings from questionnaire responses are also discussed.
Publications
Refereed Journal Publications (8):
  1. Conijn, R., Dux Speltz, E., & Chukharev-Hudilainen, E. (2024). Automated extraction of revision events from keystroke data. Reading and Writing, 37(2), 483–508. https://doi.org/10.1007/s11145-021-10222-w
  2. Anders, A., Walton, A., ​​Muhammad, A., Cabada, C., Deam, N., Dux Speltz, E., Guskaroska, A., Everett, R., Haffner, J., & Payton, C. (in press). Human-centered design for inclusive peer mentoring of graduate teaching assistants. College English, 86(2). https://doi.org/10.58680/ce202332760
  3. Anders, A., Walton, A., ​​Muhammad, A., Cabada, C., Deam, N., Dux Speltz, E., Guskaroska, A., Everett, R., & Haffner, J., & Payton, C. (2023). Inclusive collaboration: using virtual design sprints in composition programs. Computers and Composition, 70. https://doi.org/10.1016/j.compcom.2023.102806
  4. Coberley, D., Dux Speltz, E., & Zawadzki, Z. (2023). Using corpus methods to analyze modal verbs in government science communication on Twitter. Research Methods in Applied Linguistics, 2(1), 100042. https://doi.org/10.1016/j.rmal.2023.100042
  5. Dux Speltz, E., Roeser, J., & Chukharev-Hudilainen, E. (2022). Automating individualized, process-focused writing instruction: A design-based research study. Frontiers in Communication, 7:933878. https://doi.org/10.3389/fcomm.2022.933878
  6. Guskaroska, A., Dux Speltz, E., Zawadzki, Z., & Kurt, S. (2022). Students’ perceptions of emergency remote teaching in a writing course during COVID-19. Frontiers in Education, 7:965659. https://doi.org/10.3389/feduc.2022.965659
  7. Conijn, R., Dux Speltz, E., van Zaanen, M., van Waes, L., & Chukharev-Hudilainen, E. (2021). A product and process oriented tagset for revisions in writing. Written Communication, 39(1), 97–128. https://doi.org/10.1177%2F07410883211052104
  8. Dux Speltz, E., & Chukharev-Hudilainen, E. (2021). The effect of automated fluency-focused feedback on text production. Journal of Writing Research, 13(2), 231–255. https://doi.org/10.17239/jowr-2021.13.02.02

Refereed Conference Proceedings (1):
  1. Conijn, R., Dux Speltz, E., van Zaanen, M., van Waes, L., & Chukharev-Hudilainen, E. (2020). A product and process oriented tagset for revisions in writing. Proceedings of the 12th Language Resources and Evaluation Conference.

Book Reviews (1):
  1. Dux Speltz, E., & Chukharev-Hudilainen, E. (2021). Review of Writing and Language Learning: Advancing Research Agendas by Rosa M. Manchón. Journal of Writing Research, 13(2), 323–327. https://doi.org/10.17239/jowr-2021.13.02.05
The ProWrite Intelligent Tutoring System
ProWrite: Biometric technology for improving college students’ writing processes

At Iowa State University, I worked as the Postdoctoral Research Associate and Project Manager for our team’s $750,000 NSF-funded project. Through this role, I worked closely with faculty, graduate students, and undergraduate students in Dr. Evgeny Chukharev's PACE laboratory and contributed to our research project involving the automatic provision of process-focused writing feedback to students. I was responsible for designing and executing experiments, analyzing and interpreting data, reviewing literature, preparing professional presentations and scientific manuscripts, and supervising undergraduate and graduate research assistants.
Contact me for collaboration requests or other professional opportunities.
E-mail: duxspele at erau dot edu