“The era of Big Data has only just begun, but it is already important that we start questioning the assumptions, values, and biases of this new wave of research.” [1]

“The promise of learning analytics is actionable data relevant to every tier of the educational system.” [2]

“Writing program administrators, faced with increasing demands for accountability and assessment, as well as widely varying student populations, need to have ways of understanding the interactions of students, faculty, and administrators in their present program, both in the short term and longitudinally.” [3]

As writing in the twenty-first century increasingly takes place in digital spaces, where keystrokes are seamlessly translated into oceans of bytes, Writing Studies finds itself with a vast resource of data not previously imagined, explored, or applied: Big Data.

As an open and informal round-table style event founded in curiosity, we would like to invite you to come share, discuss, and ponder the promises, dangers, methods, and methodologies that Big Data and Learning Analytics hold for Writing Studies.

In particular, we hope to explore the relationships between Big Data, Learning Analytics, and:

  • Communal and individual agency
  • Evidence-based curriculum development
  • Writing assessment tools and methods
  • Writing ecologies
  • Replicable, aggregable, data-driven research

We look forward to hosting a spirited scholarly conversation, and we sincerely hope that you will joining us!


poster design by Maryam Alnaggar

Morning Plenary Session

After an introduction by Dr. Joe Moxley (USF) and plenary speaker Dr. Susan Lang (Texas Tech), each panel will feature fifteen-minute presentations by scholars that describe their research area,  theoretical fame-work, and the Big Data methods and tools used to facilitate that research. After the round of presentations, each panel will feature a fifteen-minute, moderator guided question-and-answer session where attendees are encouraged to explore the relationships between the presenters’ research theories, methods, and tools and their own research agendas.

Roger Brindley

Vice Provost and USF System Associate Vice President for USF World

Roger Brindley will welcome attendees and participants to USF and to the colloquium, acknowledge event sponsors, and introduce the Joe Moxley.

Joseph Moxley

Director of Composition at USF, and author of “Big Data, Learning Analytics, and Writing Studies,” Journal of Writing Assessment

Joe Moxley will pose the problem of the day: How are the affordances of new digital tools, such as My Reviewers, providing data and data collection methods that challenge our research practices?  How can big-data methods help us map the cognitive, interpersonal, and intrapersonal factors that impinge on collaboration, critical thinking, transfer, metacognition, and the making of knowledge?

Susan Lang

Director of Writing at Texas Tech and co-author of “Data Mining: A Hybrid Methodology for Complex and Dynamic Research”

Susan Lang will talk about the development of Raider Writer and implications of data mining for education and writing program administrators.

Moderator: Christiane Donahue. Dartmouth: Director of the Institute for Writing and Rhetoric

Break for Refreshments

Panel 1: Corpus-Based Research Using My Reviewers

Moderator: Deborah Fontaine. Chair of English/Communications and Social Sciences at Northwest Florida State College.


Zac Dixon

University of South Florida

(Co-Authored) “Everything is Illuminated: What Big Data Can Tell Us About Teacher Commentary”

Zac Dixon will describe the ways that big data creates and opens new spaces and methods for investigating writing program ecologies.

Lauren Cagle

University of South Florida

“How Teachers Talk about Research: References to Information Literacy in a Large Corpus of Writing Instructor Comments”

Lauren Cagle will discuss how big data can be mined for inquiry into specific topics like teacher’s written comments to students about information literacy.

Karen Langbehn

University of South Florida

(Co-Authored) “The Value-Add: Re-Mediating Writing Program Assessment,” Digital Writing Assessment and Evaluation

Karen Langbehn will describe how learning analytics enhance the communal agency and objectivity of writing programs.

Break for Refreshments

Panel 2: International Perspectives on Big Data and Writing Studies

Moderator: Julie Staggers. Associate Professor at the University of South Florida


Damian Finnegan

Director of the Writing Unit at Malmö University

Asko Kauppinen

Director of Research at the Writing Unit at Malmö University

“Big Data Towards Qualitative Student Learning”

Damien Finnegan and Asko Kauppinen will report on ways  My Reviewers  facilitated multiple distributed assessments of students’ work, enabling students to receive feedback from multiple faculty.

Djuddah Leijen

Head of the Centre for Academic Writing and Communication at theUniversity of Tartu

Djuddah is the first author of “Linguistic and review features of peer feedback and their effect on the implementation of changes in academic writing: A corpus based investigation” and of “Applying machine learning techniques to investigate the influence of peer feedback on the writing process” (to appear shortly).

His research focuses on predicting the effectiveness of peer review for the development of writing through the exploration of linguistic features characteristics in students’ comments. He will be exploring ways in which big data methods can inform peer review and assessment.

Break for Refreshments

Panel 3: Mapping Discourse, Composing, Engagement

Moderator: Meredith Zoetewey. Associate Professor and Director of Graduate Rhetoric and Composition at the University of South Florida


John Ackerman

Associate Director for Sustainability and Residential Life at the University of Colorado Boulder

“Writing Program Solvency and Student Engagementt”

John Ackerman will share how results of a national pilot study of the National Survey of Student Engagement helped clarify programmatic shortcomings and successes at CU-Boulder, and how the study helps build cases for the efficiency and effectiveness of campus writing instruction.

Sarah Beth Hopton

University of South Florida

“Rhetorical Geography: Mapping Discourse Using the Correspondence Feature in WordStat”

Sarah Beth Hopton will present  how correspondence analysis, using WordStat and QDAMiner, can map similarities and differences between discourse communities.

Kaitlin Clinnin

The Ohio State University

“Big MOOC, Big Data: Mining Data to Support Students’ Composing Skills”

Kaitlin Clinnin will discuss the development and use of the WExMOOC peer-review system for the analysis and reporting of student  progress in Ohio State University’s Writing II: Rhetorical Composing MOOC.

Afternoon Demonstration Sessions


Afternoon sessions will feature live demonstrations of Big Data tools guided by experienced researchers. Researchers will briefly (15 minutes) describe the context of their work, present the tools associated with that work, and demonstrate key features of their software. Presentations will be followed by a 10 minute, moderated question-and-answer session where attendees can connect their own research questions and sites to the Big Data tool.

Susan Lang

Texas Tech


Lori Salem

Temple University


Chi-Squared Automatic Interaction Detection (CHAID) analysis is an exploratory data-mining technique that can be used to discern patterns and groupings in large data sets. In writing studies, CHAID is useful for understanding the differences between and among groups (eg. students who pass or fail a particular course; students who graduate/don’t graduate, etc.).

Sarah Beth Hopton

University of South Florida


ORA is a dynamic meta-network assessment and analysis tool developed at Carnegie Mellon by the CASOS institute. It allows for the analysis of dynamic social networks and has been used to examine how networks change through space and time. Used in conjunction with AutoMap, ORA is a powerful tool with which to analyze discourse.

John Skvoretz

Professor of Sociology at the University of South Florida and Emeritus Carolina Distinguished Professor of Sociology at the University of South Carolina

Text Mining with QB and R 

QB and R are general programming tools for item and feature extraction from text files to create databases such as citation links between journals, time-stamped communications between tobacco company executives, key worded news articles, etc.

John Skvoretz is a professor of Sociology at the University of South Florida and Emeritus Carolina Distinguished Professor of Sociology from the University of South Carolina, is a Fellow of the American Association for the Advancement of Science and recipient of the 2012 James S. Coleman Distinguished Career Award from the Mathematical Sociology Section of the American Sociological Association.  Current research interests include the analysis of social and semantic networks and the development and evaluation of models for status emergence in small task groups.

Alon Friedman

Assistant Professor at the University of South Florida’s School of Information

: Data Visualization

Visualization illustrate the power of points, lines, a coordinate systems, numbers, symbols, words, shading and colors to display measured quantities, according to Tufte (1990). Alon Friedman’s presentation will focus on how we are producing visualization images using the open source R for statistical computing. He will discuss the nature of language (words) vs. visualization (images) and will compare the two by using R. Throughout his presentation, he will illustrate examples of visualization produced in R.


Related Work Published by Participants

Dixon, Z., & Moxley, J. (2013). Everything is illuminated: What big data can tell us about teacher commentary. Assessing Writing, 18(4), 241-256.

Lang, S., & Baehr, C. (2012). Data Mining: A Hybrid Methodology for Complex and Dynamic Research. College Composition and Communication, 64(1), 172-194

Langbehn, K., McIntyre, M., & Moxley, J. (2013). Re-Mediating Writing Program Assessment. In McKee, H. A., & DeVoss, D. N. (Eds.). Digital writing assessment & evaluation. Logan, UT: Computers and Composition Digital Press/Utah State University Press.

Leijen, D. A., & Leontjeva, A. (2012). Linguistic and review features of peer feedback and their effect on the implementation of changes in academic writing: A corpus based investigation. Journal of Writing Research, 4(2), 178-202.

Moxley, J. M. (2013). Big Data, Learning Analytics, and Social Assessment Methods. Journal of 6 Writing Assessment.(in-press).


[1] Boyd, D., & Crawford, K. (2012). Critical questions for big data: Provocations for a cultural, technological,and scholarly phenomenon. Information, Communication & Society, 15(5), 662-679.
[2] Johnson, L., Adams, S., Cummins, M., Estrada, V., Freeman, A., & Ludgate, H. (2013). The NMC Horizon Report: 2013 Higher Education Edition.
[3] Lang, S., & Baehr, C. (2012). Data Mining: A Hybrid Methodology for Complex and Dynamic Research. College Composition and Communication, 64(1), 172-194.

Back to top