8 Citations (Scopus)

Abstract

This study investigates how and whether information about students’ writing can be recovered from basic behavioral data extracted during their sessions in an intelligent tutoring system for writing. We calculate basic and time-sensitive keystroke indices based on log files of keys pressed during students’ writing sessions. A corpus of prompt-based essays was collected from 126 undergraduates along with keystrokes logged during the session. Holistic scores and linguistic properties of these essays were then automatically calculated using natural language processing tools. Results indicated that keystroke indices accounted for 76% of the variance in essay quality and up to 38% of the variance in the linguistic characteristics. Overall, these results suggest that keystroke analyses can help to recover crucial information about writing, which may ultimately help to improve student models in computer-based learning environments.

Original languageEnglish (US)
Pages22-29
Number of pages8
StatePublished - Jan 1 2016
Event9th International Conference on Educational Data Mining, EDM 2016 - Raleigh, United States
Duration: Jun 29 2016Jul 2 2016

Conference

Conference9th International Conference on Educational Data Mining, EDM 2016
CountryUnited States
CityRaleigh
Period6/29/167/2/16

Fingerprint

Time series
Students
Linguistics
Intelligent systems
Processing

Keywords

  • Feedback
  • Intelligent tutoring systems
  • Keystrokes
  • Natural language processing
  • Temporality
  • Writing

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Allen, L. K., Jacovina, M. E., Dascalu, M., Roscoe, R., Kent, K. M., Likens, A. D., & McNamara, D. (2016). {ENTER}ing the time series {SPACE}: Uncovering the writing process through keystroke analyses. 22-29. Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.

{ENTER}ing the time series {SPACE} : Uncovering the writing process through keystroke analyses. / Allen, Laura K.; Jacovina, Matthew E.; Dascalu, Mihai; Roscoe, Rod; Kent, Kevin M.; Likens, Aaron D.; McNamara, Danielle.

2016. 22-29 Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.

Research output: Contribution to conferencePaper

Allen, LK, Jacovina, ME, Dascalu, M, Roscoe, R, Kent, KM, Likens, AD & McNamara, D 2016, '{ENTER}ing the time series {SPACE}: Uncovering the writing process through keystroke analyses' Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States, 6/29/16 - 7/2/16, pp. 22-29.
Allen LK, Jacovina ME, Dascalu M, Roscoe R, Kent KM, Likens AD et al. {ENTER}ing the time series {SPACE}: Uncovering the writing process through keystroke analyses. 2016. Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.
Allen, Laura K. ; Jacovina, Matthew E. ; Dascalu, Mihai ; Roscoe, Rod ; Kent, Kevin M. ; Likens, Aaron D. ; McNamara, Danielle. / {ENTER}ing the time series {SPACE} : Uncovering the writing process through keystroke analyses. Paper presented at 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States.8 p.
@conference{17ed7e11722b48f48c6b27fc1c00b5e4,
title = "{ENTER}ing the time series {SPACE}: Uncovering the writing process through keystroke analyses",
abstract = "This study investigates how and whether information about students’ writing can be recovered from basic behavioral data extracted during their sessions in an intelligent tutoring system for writing. We calculate basic and time-sensitive keystroke indices based on log files of keys pressed during students’ writing sessions. A corpus of prompt-based essays was collected from 126 undergraduates along with keystrokes logged during the session. Holistic scores and linguistic properties of these essays were then automatically calculated using natural language processing tools. Results indicated that keystroke indices accounted for 76{\%} of the variance in essay quality and up to 38{\%} of the variance in the linguistic characteristics. Overall, these results suggest that keystroke analyses can help to recover crucial information about writing, which may ultimately help to improve student models in computer-based learning environments.",
keywords = "Feedback, Intelligent tutoring systems, Keystrokes, Natural language processing, Temporality, Writing",
author = "Allen, {Laura K.} and Jacovina, {Matthew E.} and Mihai Dascalu and Rod Roscoe and Kent, {Kevin M.} and Likens, {Aaron D.} and Danielle McNamara",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
pages = "22--29",
note = "9th International Conference on Educational Data Mining, EDM 2016 ; Conference date: 29-06-2016 Through 02-07-2016",

}

TY - CONF

T1 - {ENTER}ing the time series {SPACE}

T2 - Uncovering the writing process through keystroke analyses

AU - Allen, Laura K.

AU - Jacovina, Matthew E.

AU - Dascalu, Mihai

AU - Roscoe, Rod

AU - Kent, Kevin M.

AU - Likens, Aaron D.

AU - McNamara, Danielle

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This study investigates how and whether information about students’ writing can be recovered from basic behavioral data extracted during their sessions in an intelligent tutoring system for writing. We calculate basic and time-sensitive keystroke indices based on log files of keys pressed during students’ writing sessions. A corpus of prompt-based essays was collected from 126 undergraduates along with keystrokes logged during the session. Holistic scores and linguistic properties of these essays were then automatically calculated using natural language processing tools. Results indicated that keystroke indices accounted for 76% of the variance in essay quality and up to 38% of the variance in the linguistic characteristics. Overall, these results suggest that keystroke analyses can help to recover crucial information about writing, which may ultimately help to improve student models in computer-based learning environments.

AB - This study investigates how and whether information about students’ writing can be recovered from basic behavioral data extracted during their sessions in an intelligent tutoring system for writing. We calculate basic and time-sensitive keystroke indices based on log files of keys pressed during students’ writing sessions. A corpus of prompt-based essays was collected from 126 undergraduates along with keystrokes logged during the session. Holistic scores and linguistic properties of these essays were then automatically calculated using natural language processing tools. Results indicated that keystroke indices accounted for 76% of the variance in essay quality and up to 38% of the variance in the linguistic characteristics. Overall, these results suggest that keystroke analyses can help to recover crucial information about writing, which may ultimately help to improve student models in computer-based learning environments.

KW - Feedback

KW - Intelligent tutoring systems

KW - Keystrokes

KW - Natural language processing

KW - Temporality

KW - Writing

UR - http://www.scopus.com/inward/record.url?scp=85027513354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027513354&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85027513354

SP - 22

EP - 29

ER -