@inproceedings{schaller-etal-2026-genius,
title = "{GENIUS} Keylog Corpus - a {G}erman High School Student Corpus with Keystroke Logging Data",
author = {Schaller, Nils-Jonathan and
Jansen, Thorben and
H{\"o}ft, Lars and
P{\"u}njer, Hannah and
Horbach, Andrea},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.550/",
doi = "10.63317/4zdv5j2yj6vg",
pages = "6919--6928",
abstract = "Student writing has been studied either as a final product (arguments in an already written text) or as a writing process (keystroke data), but not in an integrated manner. We present Anonymised Keylog Corpus, the first publicly available dataset (as far as we know) that combines both comprehensive argumentative annotations with keystroke logging (259 German argumentative essays written by high school students). Our analysis reveals that 96{\%} of students wrote linearly without recursion and 88{\%} omitted the conclusion section. Writing was mainly characterised by fluent writing without extensive pauses, mainly due to the time limit for completing the task. Additionally we suggest methodology on how to combine annotations with keystroke events and carried out an explorative analysis of writer profiles."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schaller-etal-2026-genius">
<titleInfo>
<title>GENIUS Keylog Corpus - a German High School Student Corpus with Keystroke Logging Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nils-Jonathan</namePart>
<namePart type="family">Schaller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thorben</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Höft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Pünjer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Student writing has been studied either as a final product (arguments in an already written text) or as a writing process (keystroke data), but not in an integrated manner. We present Anonymised Keylog Corpus, the first publicly available dataset (as far as we know) that combines both comprehensive argumentative annotations with keystroke logging (259 German argumentative essays written by high school students). Our analysis reveals that 96% of students wrote linearly without recursion and 88% omitted the conclusion section. Writing was mainly characterised by fluent writing without extensive pauses, mainly due to the time limit for completing the task. Additionally we suggest methodology on how to combine annotations with keystroke events and carried out an explorative analysis of writer profiles.</abstract>
<identifier type="citekey">schaller-etal-2026-genius</identifier>
<identifier type="doi">10.63317/4zdv5j2yj6vg</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.550/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6919</start>
<end>6928</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GENIUS Keylog Corpus - a German High School Student Corpus with Keystroke Logging Data
%A Schaller, Nils-Jonathan
%A Jansen, Thorben
%A Höft, Lars
%A Pünjer, Hannah
%A Horbach, Andrea
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F schaller-etal-2026-genius
%X Student writing has been studied either as a final product (arguments in an already written text) or as a writing process (keystroke data), but not in an integrated manner. We present Anonymised Keylog Corpus, the first publicly available dataset (as far as we know) that combines both comprehensive argumentative annotations with keystroke logging (259 German argumentative essays written by high school students). Our analysis reveals that 96% of students wrote linearly without recursion and 88% omitted the conclusion section. Writing was mainly characterised by fluent writing without extensive pauses, mainly due to the time limit for completing the task. Additionally we suggest methodology on how to combine annotations with keystroke events and carried out an explorative analysis of writer profiles.
%R 10.63317/4zdv5j2yj6vg
%U https://aclanthology.org/2026.lrec-1.550/
%U https://doi.org/10.63317/4zdv5j2yj6vg
%P 6919-6928
Markdown (Informal)
[GENIUS Keylog Corpus - a German High School Student Corpus with Keystroke Logging Data](https://aclanthology.org/2026.lrec-1.550/) (Schaller et al., LREC 2026)
ACL