- Keywords
- AI writing;keystroke logging;keystroke logging data processing and analysis;on-line writing and digital media
- Domain
- Learning and Instructional Technology
Abstract
Inputlog is a widely
used keystroke logging tool for observing and analyzing writing processes. This
demo introduces the major new features of Inputlog 9.6.0 and outlines planned
future developments.Versioning and
Diary Function
A new automatic versioning option allows users to save intermediate Word
document versions at fixed intervals (e.g., every three minutes). Researchers
can compare these versions to track document changes throughout the writing
session.
An optional diary prompt in the closing wizard invites writers to comment on
their session, facilitating the combination of process data and self-report.Expanded Logging
Environments
Because writing increasingly takes place outside MS Word, the logging
environment has been expanded. Inputlog now offers dedicated logging modules
for Google Docs and LibreOffice, broadening the range of authentic writing
contexts that can be captured.Feedback Reports
Inputlog generates student-centered feedback reports that visualize key process
indicators, including process graphs and source interaction. Users may rely on
the default template or customize report formats to meet instructional or
research needs, such as the use of AI.Multilingual
Logging
New beta versions introduce preliminary support for logging Korean and Chinese
script (via Pinyin). This extends Inputlog’s previous focus on Latin-based
scripts and broadens its applicability in multilingual writing research. Copy-Task Dashboard
Inputlog includes a standardized copy task designed to assess typing skills in thirteen
languages using sentences, word triplets, and letter clusters. We also present
a corpus of more than 5,000 anonymized copy-task recordings, accompanied by an
interactive R-Shiny dashboard that allows researchers to explore the corpus,
download data, and benchmark their own results.
- Keywords
- data visualisation;keystroke logging data processing and analysis;learning to write;writing at school
- Domain
- Learning and Instructional Technology
Abstract
Approaches
to writing based on keystroke logging are becoming increasingly prevalent and
are contributing to a more profound understanding of the writing process. A
plethora of software programs facilitate the recording of keystrokes, thereby
enabling the analysis of both the temporal and spatial dimensions of writing,
from a recording file called a log. However,
the interpretation of the information contained within these logs is
challenging, due to the atypical nature of the data. The GIS
representation has been utilised extensively (Becotte et al. 2019). Ggxlog
is a recently developed software program that aims to combine text genetics
(Leblay & Leblay 2019) and graph theory with keystroke logging
(Caporossi & Leblay 2011; Doquet & Leblay 2014). This ggxlog software
offers a specific feature, designated 'progressive graph', which enables
researchers or educators to visualise the various stages of a writing session
that has taken place (Usoof et al. 2020). This innovative feature
enables the text being written to be displayed simultaneously, as in a word
processor, alongside the real-time construction of the corresponding graph. The
objective of this study is to collect a common pilot corpus between Finland,
France and Quebec in a school context, with a focus on brief pieces of writing,
referred to as 'toy examples'. This study will examine how young learners use
keyboards to facilitate their acquisition of writing skills, thereby marking a
pivotal transition from the conventional paper-and-pencil medium
(Auriac-Slusarczyk et al., 2013; Cogis & Leblay, 2010). This would
facilitate a more profound understanding of the utilisation of technological
resources in the acquisition of written French and written Finnish as first
languages.
- Keywords
- keystroke logging data processing and analysis;natural language processing (NLP);writing models;writing processes
- Domain
- -
Abstract
We present an open-source tool for analyzing writing process data in relation to linguistic structures: THEtool(https://github.com/mulasik/wta; Mahlow 2024; Ulasik and Miletic 2024; Ulasik et al. 2025). Although linguistic modeling of the writing process has gained importance in recent years, existing approaches, whether rooted in linguistic theory or writing research, remain insufficient to explain how writers actually produce and revise text at a linguistic level. THEtool enables writing researchers to investigate the writing process with a particular focus on sentences and their interaction with writing bursts and revisions. Because the software operates fully automatically and requires no manual intervention, it facilitates the efficient processing of large datasets. THEtool processes keystroke logging data in the XML-based IDFX format generated by Inputlog and ScriptLog, the de facto standard for storing and exchanging writing process data, thereby ensuring seamless integration with existing tools and workflows.To support a wide range of research applications, THEtool offers configurable key features, including language selection (currently German, Greek, French, and English, with straightforward extensibility to additional languages), the minimum pause duration that triggers the extraction of text and sentence versions within a writing burst, and relevance parameters for filtering text versions.THEtool is a fully functioning implementation of a model of text production based on the concept of layers: writing bursts, revisions, and sentence production are conceptualized as three distinct yet interacting layers that share a common timeline. Bursts may be interrupted by revision episodes or, in an abstract sense, by final punctuation marks signaling sentence completion. Revision processes can be interrupted by pauses or segmented by final punctuation. Likewise, sentence production may be interrupted by pauses or revisions. Projecting these layers onto one another enables new insights into the writing process from a linguistic perspective.We conducted exploratory studies in German, Greek, French, and English using THEtool. The results demonstrate both the feasibility and the analytical potential of the proposed approach.
- Keywords
- evaluation and assessment of writing competence;feedback;Generative AI;natural language processing (NLP)
- Domain
- Assessment and Evaluation
Abstract
Feedback is widely recognised
as one of the most powerful influences on learning, particularly in the
development of writing competence. However, in everyday classroom practice, the
provision of detailed and timely feedback on student texts is constrained by
limited time resources. Automated essay scoring (AES) has the potential to
mitigate this tension, provided that it is pedagogically sound and sensitive to
the complexity of writing.This demonstration
introduces an AI-based AES system developed for primary and lower secondary education.
The system generates structured feedback within seconds, addressing four core
dimensions of writing: content quality, coherence and cohesion, language
accuracy, and stylistic appropriateness. In addition to score-based ratings
across eight criteria, the system provides qualitative, dimension-specific
feedback designed to support formative learning processes.The development of the
system builds on a large empirical foundation of 36,739 digitised student
essays that were evaluated by trained human raters. By combining large language
models with targeted natural language processing techniques and educational
assessment frameworks, the system aims to produce automated feedback that is
more consistent, transparent, and pedagogically grounded than that of
general-purpose AI applications. The demonstration briefly outlines these
design principles and explains the rationale underlying the selected feedback
dimensions.The demonstration then
focuses on how these principles are operationalised in practice. Participants
are shown how the system structures multi-dimensional feedback, generates
qualitative comments from textual features, and presents feedback in an
interpretable manner for educational use. Particular attention is given to
interface and feedback design choices that support formative use in the
classroom and clearly differentiate the system from generic AI-based writing
tools.Overall, the demonstration
contributes to current discussions on AI in writing education by illustrating
how automated feedback systems can be designed to augment instructional
practice and support learning in classroom contexts.
- Keywords
- academic writing;AI writing;assessment;evaluation and assessment of writing competence
- Domain
- Learning and Instructional Technology
Abstract
The development of academic writing skills in higher education presents
numerous challenges. Instructors face high workloads alongside the ongoing need
to provide focused and pedagogically sound feedback. While AI tools can assist
in this area, current solutions show limitations. Automated writing assessment
tools tend to focus on surface‑level language features
(Zhao, 2025), and generative AI feedback may suffer from hallucinations, fail
to address specific criteria, or lack alignment with teaching content
(Gautschi, 2025). In addition, fine‑tuning large language
models for specialized purposes—and many paid solutions—may be cost‑prohibitive.Recent developments in GenAI, particularly retrieval‑augmented generation (RAG) systems, offer a promising alternative (Li et al., 2025; Swacha & Gracel, 2025). Although RAG‑based architectures have been applied to academic writing support, to
date they have not been applied to the specific problem of academic writing
assessment for thesis writing. Existing tools such as CorpusChat (see Cheung
& Crosthwaite, 2025) demonstrate RAG‑based support for student writers but do not include an assessment
component. To our knowledge, no existing tool integrates RAG for assessment
with the goal of providing feedback aligned with instructor or writing program
specifications.To address these issues, we have developed a RAG‑based system for generating formative feedback. This approach allows for
reduced hallucination, greater focus, and improved flexibility and control over
generated feedback. Our SaaS‑independent multi‑chat, multi‑context RAG application
(Node.js server, React frontend) incorporates user and persistence management,
full handling of multiple RAG document contexts, recursive splitting, vector
storage (Qdrant), and query rewriting to optimize similarity searches. Local
context folders include target structures for feedback, target criteria, and
samples of evaluated texts. The system provides feedback based on a modified
IMRD‑based structure model
for thesis writing. This demonstration session showcases the system’s potential to promote
academic writing skills in higher education, benefiting both students and
lecturers through a flexible, pedagogically grounded formative feedback
ecosystem.
- Keywords
- eye tracking;handwriting;writing and linguistics;writing impairment
- Domain
- Learning and Special Education
Abstract
During this demonstration, we aim to present an
innovative experimental setup for collecting both offline (linguistic choices)
and real-time (online, pauses, speed, duration, etc.) data, including
eye-tracking data, for the same individual during both reading and writing
tasks: DYSTRACKER device (Anonymisation). This device linked to a research
project with the same name is the result of a transdisciplinary collaboration
implying several disciplines (psycholinguistic, linguistic, speech therapy,
neuroscience, computer science and orthoptics) and a company (Sierra
Neurovision, France). Sierra Neurovision designs and develops eye-trackers to
improve screening for neurovisual disorders in adolescents and young adults.Obtaining all these indicators for the same person
in both reading and writing was a technical and scientific challenge. Data were
collected using this innovative setup, which integrates a pen tablet, an eye-tracker,
and their associated software. The written data will be collected using
high-resolution pen tablets (Wacom One or similar) with Eye and Pen© software
(Chesnet and Alamargot, 2005). This software records writing and eye activity.
For eye activity, we will use the Eya S360 eye-tracker (SIERRA Neurovision, CE
standard - ISO 62471), which records and displays eye movements. We will obtain
data (enabling us to analyze lexical choices (off-line analysis), real-time
processes (on-line analysis - pauses, flow, revisions, etc.), including ocular
data (saccades, rhythms, etc.)) from written texts and readings.As said before, the device was developed for a
previous project (a pilot study funded by a laboratory of excellence and the
École Normale Supérieure of Lyon). It is also fully operational and has enabled
the collection of these types of data for 44 students with and without dyslexia
(Mazur, Quignard and Bigarnet, accepted). This setup indeed was therefore
implemented to study the impact of dyslexia/dysorthographia on the reading and
writing processes of students, contributing to a better understanding of this
disorder and its impact.Chesnet,
D. & Alamargot, D. (2005). Analyses en temps réel des activités oculaires
et graphomotrices du scripteur : intérêt du dispositif 'Eye and Pen'. L'Année Psychologique, 105, 477-520.This demonstration is combined with a paper submission (30645).
- Keywords
- academic writing;AI writing;EFL and ESL writing;writing tools and writing technology
- Domain
- Learning and Instructional Technology
Abstract
The challenge
of creating a coherent text: A Coherence-Focused AI Chatbot for Academic
Writing Despite growing interest in
AI-supported writing instruction, relatively little is known about how interactive
AI tools affect higher-order writing skills, such as textual coherence. To
address this gap, we present the development of a coherence-focused feedback
chatbot designed explicitly for research-based writing. The tool aims to
translate writing research on cohesion and coherence into practical, real-time
guidance in academic writing for students and early career academics.The tool is grounded in cohesion
theory, which explains how linguistic features create unity and continuity
across a text (Crossley et al., 2016; Halliday & Hasan, 2014; Morris et al.,
2025). The coherence-focused chatbot was developed focusing on these
cohesion theory frameworks, through iterative prompt engineering, and
integrated into the free, online De-jargonizer platform (Rakedzon et al., 2017). The chatbot provides individualized,
question-driven prompts that guide students in identifying aspects of
coherence, such as lexical overlap across sentences/paragraphs, semantic
similarity between ideas, and use of transitions. At each stage, they receive
AI-generated suggestions and revise their texts across iterations. A reflection
and a questionnaire on the process follow this. During the demonstration, attendees
will receive an overview of the pedagogical rationale, tool development, and use
in research design, followed by a demonstration of the chatbot. Participants
will be invited to test the tool on their own writing samples and explore how
coherence indices are employed to generate tailored feedback. The project demonstrates
how research can be translated into classroom-ready practice, advancing
understanding of AI’s potential to support higher-order writing skills in
multilingual contexts. More broadly, it highlights how coherence-aware AI tools
can contribute to more inclusive, adaptive, and discipline-responsive academic
writing instruction.