CoChat
Sign Up
Cited by 23Artificial Intelligence in EducationScience Education and PedagogyVisual and Cognitive Learning Processes

An integrated concept mapping and image recognition approach to improving students' scientific inquiry course performance

Huang, Hsiu‐Ling, Hwang, Gwo‐Jen, Chen, Pei‐Ying·2022·British Journal of Educational Technology
DOI 10.1111/bjet.13177
Open this paper in CoChat — free account

Abstract

Scholars and researchers generally believe that scientific inquiry is an important activity for cultivating students' applied knowledge and high‐level thinking ability. The process of scientific inquiry can promote students' learning motivation and trigger their higher‐order thinking ability. However, students may not have enough prior knowledge or they may lack inquiry experience, which may influence the effectiveness of their inquiry learning. Besides, in a scientific inquiry environment assisted by technology, students must face abundant and diverse learning resources, and may not effectively organize and carry out advanced cogitation to solve problems. Therefore, this research proposed an integrated concept mapping and image recognition (IR) approach to help students effectively acquire and organize knowledge in the process of scientific inquiry. This study applied a quasi‐experimental design to verify the effect of this proposed approach. The experimental group conducted the concept mapping‐based IR (CM‐IR) learning approach, whilst the control group conducted the conventional IR‐based learning approach to evaluate the students' performance in terms of their learning motivation and learning achievements. The participants were two classes of 10th‐grade students in northern Taiwan. One was the experimental group with 22 students, whilst the other was the control group with 22 students. The experimental results show that the students learning with the CM‐IR learning approach had better learning achievement, attitudes and intrinsic motivation, as well as higher mental load than those learning with the conventional IR‐based learning approach. Accordingly, several suggestions are provided for future research in this field. Practitioner notes: What is already known about this topic With the development of information technology, AI has attracted the attention of researchers. Image recognition (IR) is one of the AI applications, and has been used to support learning in various educational fields. Researchers have indicated that concept mapping is an effective instructional strategy and promotes students' knowledge construction. What this paper adds A concept mapping‐based IR (CM‐IR) learning approach is proposed to improve students' scientific inquiry performance. A quasi‐experimental design was conducted with 10th‐grade students on the ‘Plant identification’ unit of the scientific inquiry course. The experimental results show that the proposed approach can significantly improve students' learning achievement, learning motivation and learning attitude. Implications for practice and/or policy The CM‐IR learning approach could be an effective method to facilitate students' learning performances and motivation in scientific inquiry. It is worth promoting the CM‐IR learning approach in school settings since it is low‐cost and enables learning anywhere using mobile devices. Scholars and educators are encouraged to work on how AI technologies applications can be applied to support learning.

Integrity signals

Registry

Crossref · 10.1111/bjet.13177

Cites

91 of 91 references verified0 citation errors · 0 not checkable

Statistics

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

Claims the paper makes

This paper’s full text isn’t openly available, 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?

  • The choice of concept map construction mode and whether construction is student- or teacher-led are still hot topics that urgently need deeper exploration.

    “The choice of concept map construction mode, that is, whether students should construct concept maps individually or collaboratively (Aşıksoy, 2019; Fang, 2023), and whether the construction process is student- or teacher-led (Huang et al., 2022; Hwang et al., 2023), are still hot topics in the current research and urgently need to be explored and answered in greater depth.”

    From Concept mapping in STEM education: a meta-analysis of its impact on students' achievement (2004–2023) (2025) · cites this paper as Huang et al., 2022

Cites

Flagged first, then by citations

1 of the 92 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Huang, H., Hwang, G., & Chen, P.
Affiliations
National Taiwan University of Science and Technology (TW)
Corresponding author
Hwang, Gwo‐Jen
ORCID
Venue
British Journal of Educational Technology
Publisher
Wiley
Published
2021-12-20
Volume
53
Issue
3
Pages
706-727
ISSN
  • 0007-1013 (ISSN-L)
  • 1467-8535
DOI
10.1111/bjet.13177
OpenAlex
W4200055979
Cited by
20
References
92
Citations by year
2026: 7 · 2025: 6 · 2024: 2 · 2023: 4 · 2022: 1
FWCI
1.58
Type
journal article
Language
en
Open access
closed
Licence
Locations
British Journal of Educational Technology (publishedVersion)
Funders
Ministry of Science and Technology, Taiwan (MOST‐109‐2511‐H‐011‐002‐MY3, MOST‐108‐2511‐H‐011‐005‐MY3)
Topics
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Social Sciences › Education › Science Education and Pedagogy
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Visual and Cognitive Learning Processes
Keywords
concept mapping, image recognition, scientific inquiry, inquiry-based learning, student motivation, intrinsic motivation, academic performance, mental workload, plant identification, knowledge organization, artificial intelligence in education, mobile learning, high school students

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