CoChat
Sign Up
Cited by 31Artificial Intelligence in EducationAI in Service InteractionsIntelligent Tutoring Systems and Adaptive Learning

From prompt to polished: Exploring student-chatbot interactions for academic writing assistance

Open access
Usher, Maya, Amzalag, Meital·2025·Education Sciences
DOI 10.3390/educsci15030329
Open this paper in CoChat — free account

Abstract

The integration of generative artificial intelligence (GenAI) in higher education has opened new avenues for enhancing academic writing through student–chatbot interactions. While initial research has explored this potential, deeper insights into the nature of these interactions are needed. This study characterizes graduate students’ interactions with AI chatbots for academic writing, focusing on the types of assistance they sought and their communication style and tone patterns. To achieve this, individual online sessions were conducted with 43 graduate students, and their chatbot interactions were analyzed using qualitative and quantitative methods. The analysis identified seven distinct types of assistance sought by students. The most frequent requests involved content generation and expansion, followed by source integration and verification, and then concept clarification and definitions. Students also sought chatbot support for writing consultation, text refinement and formatting, and, less frequently, rephrasing and modifying content and translation assistance. The most frequent communication style was “requesting,” marked by direct appeals for assistance, followed by “questioning” and “declarative” styles. In terms of communication tone, “neutral” and “praising” appeals dominated the interactions, reflecting engagement and appreciation for chatbot responses, while “reprimanding” tones were relatively low. These findings highlight the need for tailored chatbot intervent…

Integrity signals

Registry

Crossref · 10.3390/educsci15030329

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Human oversight remains essential for ensuring the correctness, efficiency, and security of AI-generated outputs.

    “While GenAI tools have streamlined many aspects of learning in higher education, human oversight remains essential for ensuring the correctness, efficiency, and security of AI-generated outputs (Usher, 2025).”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Usher, 2025

  • The inconsistency and occasional inaccuracy of AI outputs, particularly in conceptually complex or creative tasks, highlight the need for human oversight and strong foundational knowledge.

    “Moreover, the inconsistency and occasional inaccuracy of AI outputs, particularly in conceptually complex or creative tasks, highlight the need for human oversight and strong foundational knowledge (Holmes et al., 2022;Usher, 2025).”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Usher, 2025

  • Prior studies on GenAI integration in higher education have underscored the importance of scaffolding, transparent assessment criteria, and guided practice, demonstrating that the way GenAI tools are introduced critically shapes students' abilities to use them effectively.

    “Prior studies on GenAI integration in higher education have underscored the importance of scaffolding, transparent assessment criteria, and guided practice, demonstrating that the way GenAI tools are introduced critically shapes students' abilities to use them effectively (Garg et al., 2025;Usher, 2025).”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Usher, 2025

  • These mixed views reflect broader debates in the literature on the dual nature of AI in education.

    “These mixed views reflect broader debates in the literature on the dual nature of AI in education -simultaneously enhancing productivity and creativity while raising concerns about over-dependence and diminished cognitive engagement (Mogavi et al., 2024;Usher, 2025;Zviel-Girshin, 2024).”

    From Integrating Generative AI into Programming Education: Student Perceptions and the Challenge of Correcting AI Errors (2025) · cites this paper as Usher, 2025

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Usher, M., & Amzalag, M.
Affiliations
Holon Institute of Technology (IL)
Corresponding author
Usher, Maya
ORCID
Venue
Education Sciences
Publisher
MDPI AG
Published
2025-03-07
Volume
15
Issue
3
Pages
329
ISSN
2227-7102 (ISSN-L)
DOI
10.3390/educsci15030329
OpenAlex
W4408170563
Cited by
31
References
22
Citations by year
2026: 20 · 2025: 11
FWCI
32.50
Type
journal article
Language
en
Open access
Licence
Locations
  • Education Sciences (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
Keywords
academic writing support, generative AI, AI chatbots, graduate students, communication styles, communication tone, content creation, source integration, writing consultation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review