Next Article in Journal
A Survey on Digital Trust: Towards a Validated Definition
Previous Article in Journal
Leveraging Large Language Models for Clinical Trial Eligibility Criteria Classification
 
 
Article
Peer-Review Record

A Pilot Study on AI-Powered Gamified Chatbot with OMO Strategy for Enhancing Parental Nutrition Knowledge†

by Han Chun Huang 1,* and Hsiao Wen Chuang 2
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Submission received: 10 February 2025 / Revised: 23 April 2025 / Accepted: 25 April 2025 / Published: 30 April 2025

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Dear Authors,

Your study presents an innovative and timely exploration of how gamified chatbots combined with Online Merge Offline (OMO) strategies can enhance parental nutrition education. The integration of mHealth, AI-driven chatbots, and gamification is highly relevant to modern digital health interventions. Below are some constructive suggestions to further improve the clarity, depth, and impact of your paper:

  1. INTRODUCTION

The introduction provides a good starting point for the study, outlining the increasing role of mobile health (mHealth) solutions, chatbots, and gamification in healthcare interventions. The authors also introduce the Online Merge Offline (OMO) strategy, highlighting its potential in bridging digital and in-person engagement. However, there are areas where the introduction could be improved to provide a stronger foundation for the research.

* Expand the discussion on gamification and chatbot effectiveness in mHealth: While the introduction mentions gamified chatbots, it does not fully explore why gamification enhances engagement in health interventions. The authors should reference more studies on gamification in health education to strengthen the justification.

* Clarify the role of OMO in health interventions: The OMO concept is introduced but not fully explained in relation to healthcare. The authors reference OMO in business and retail settings, but they should provide more examples of its successful application in health education.

* Strengthen the literature review and citations: Some key references on mHealth, chatbots, and gamification are missing. It would be beneficial to include recent studies on gamified chatbot interventions in healthcare to support the theoretical foundation.

* Make the research gap more explicit: The introduction provides general background information, but it does not clearly define the research gap that this study aims to fill. A clear statement about what has been done in the field and what remains unexplored would help position the study more effectively.

Overall, the introduction is informative and relevant, but it needs more theoretical depth and stronger references to fully justify the study. Strengthening the discussion on gamification, OMO, and chatbot effectiveness will make the paper more compelling.

  1. Research Design

The research design is generally well-structured and aligns with the study’s objective of evaluating the effectiveness of a gamified chatbot using the OMO strategy for parental nutrition education. However, there are areas where methodological clarity and justification could be improved to enhance the study’s rigor and credibility.

* Small sample size & lack of control group: The study only included 20 participants, which is a very small sample size for drawing strong conclusions. There is no control group, meaning we cannot determine whether improvements in knowledge were due to the chatbot, the offline seminars, or other external factors. So, future studies should include a larger sample size and a control group (e.g., parents attending traditional nutrition seminars without chatbot support) to improve validity.

* Limited duration of the study: The intervention lasted only eight weeks, which may not be sufficient to evaluate long-term retention of knowledge or behavioral change. So, a longitudinal study (e.g., follow-up tests after 3–6 months) would help assess whether participants retain the information over time.

* No qualitative insights on user experience: The study primarily uses quantitative measures (pre-test/post-test scores) but does not include qualitative feedback from participants. Understanding how parents perceived the chatbot (e.g., Was it easy to use? Was it engaging? Did it motivate behavior change?)  would add more depth. So, including surveys or interviews to gather user feedback on engagement, usability, and effectiveness would provide valuable insights.

* Need for more justification of the statistical methods: While the paired-sample t-test is appropriate for analyzing pre-test and post-test differences, other statistical approaches could add more depth. Report effect sizes (e.g., Cohen’s d) to assess the magnitude of the chatbot’s impact. If possible, consider using ANOVA or regression analysis to evaluate whether factors like age, education level, or previous nutrition knowledge influenced the results.

Overall, the research design is appropriate for a pilot study, but it has limitations in sample size, lack of a control group, and short study duration. Addressing these issues in future research would improve the validity, reliability, and practical applicability of the findings.

  1. Methodology Description

The Methods section provides a general overview of the study's approach, but some details are missing or require further clarification to ensure full transparency and reproducibility.

* Lack of detail on sample selection and demographics: The study states that 20 parents participated, but there is no clear explanation of how they were recruited (e.g., voluntary participation, random selection, invitation criteria). How were participants screened for eligibility? Did they have prior nutrition knowledge or chatbot experience? So, provide a clearer description of inclusion/exclusion criteria and participant recruitment strategy.

* Unclear randomization and control measures: There is no control group, meaning the study does not account for alternative explanations of knowledge improvement (e.g., general exposure to nutrition information outside the study). So, a future study should compare participants using the chatbot vs. those who attend only traditional seminars to determine the chatbot's true effect.

* Insufficient explanation of statistical analysis: Were assumptions of the t-test (e.g., normality of data) checked? So, include a more detailed explanation of statistical methods, assumptions, and any additional tests conducted.

No discussion of potential biases or limitations: The study does not acknowledge potential biases, such as: (1) Self-selection bias (motivated parents may be more likely to participate). (2) Social desirability bias (parents may over-report their knowledge to appear more engaged). So, add a limitations section acknowledging these potential biases and how they were (or could be) mitigated.

* Missing information on chatbot engagement metrics: While the chatbot features are described, no data is provided on engagement levels (e.g., how frequently parents used the chatbot, how many quizzes they completed, average interaction duration). If possible, include chatbot usage statistics to assess how much participants engaged with the intervention.

Overall, the Methods section is adequately structured but lacks detail in key areas such as participant selection, statistical analysis, and chatbot engagement metrics. Expanding on these aspects will enhance transparency and replicability of the study.

  1. Results Presentation

The Results section is generally well-structured, but some areas require improvement to ensure clarity, completeness, and stronger alignment with the study's objectives.

* No Data on Chatbot Engagement and Usage: The paper describes chatbot features but does not report how often participants interacted with it. Were participants actively engaging with quizzes and video content, or were they passive users?

* Unclear Influence of Gamification on Learning Outcomes: The study introduces leaderboards and rankings, but there is no analysis of whether these features influenced engagement or learning outcomes. If possible, compare knowledge gains between highly engaged vs. less engaged users to see if gamification had an impact.

* The Results section only assesses short-term knowledge improvement. It does not discuss whether participants retained this knowledge over time or applied it in real life. So, a follow-up study (e.g., post-test after 3–6 months) would help assess long-term retention and behavior change.

  1. Conclusions

The Conclusions section effectively summarizes the study’s key findings and implications. However, while it is generally aligned with the results, certain claims require further justification or expansion based on the presented data.

* Overgeneralization of findings: The conclusion suggests that gamified chatbots with OMO strategies can improve nutrition knowledge broadly, but this study was limited to 20 participants in one setting. So, reword claims to reflect the small sample size and limited scope (e.g., “Preliminary findings suggest…” or “Results indicate potential for…”).

* No mention of engagement metrics: The paper’s conclusion emphasizes knowledge improvement but does not discuss engagement with the chatbot (e.g., quiz completion rates, time spent interacting). So, if engagement data was collected, include it to reinforce the argument that gamification enhanced participation.

* Limited discussion of gamification’s effectiveness: The study introduces leaderboards and level completion mechanisms but does not analyze whether these influenced learning outcomes. So, the conclusion should acknowledge that the specific impact of gamification was not measured, and future research should investigate this.

* Lack of behavioral impact assessment: The study measures knowledge improvement, but does not assess whether parents applied their learning in real life (e.g., changing their children’s diets). So, acknowledge this limitation and suggest future research on behavioral changes resulting from chatbot interventions.

* No discussion on long-term retention: The study measures knowledge immediately after the intervention but does not test whether parents retain this information over time. So, suggest a follow-up study to evaluate whether knowledge gains persist 3–6 months later.

Overall, the conclusions are mostly supported by the results, but they would be stronger with a more cautious tone, a discussion of engagement metrics, and acknowledgment of behavioral and long-term retention limitations. Strengthening these areas will improve the credibility and real-world applicability of the study’s findings.

  1. References

The references cited in the manuscript are generally relevant and appropriate for the research topic, covering key areas such as mHealth, chatbots, gamification, and OMO (Online Merge Offline) strategies. However, there are some gaps and areas for improvement that could strengthen the study's theoretical foundation.

* Use of empirical studies and reports

* Insufficient references on OMO in healthcare

* Few citations for statistical methods used

* Lack of recent mHealth and gamification Studies: While some foundational papers are cited, there is limited use of recent (2022-2024) studies on: (1) mHealth interventions for nutrition education; (2) Gamified chatbots for behavior change; and (3) User engagement and retention in digital health programs. So, add newer studies (from the last 3 years) on mHealth and gamification, particularly those applying behavioral change theories.

  • Limited discussion on chatbot effectiveness in nutrition education: Cite studies that evaluate AI-driven chatbots for dietary counseling, weight management, or food tracking.
  1. English Language

* Some sentences are overly long and complex, making them harder to read. Example: "The functions and impact of mobile phones have reached an unprecedented high point for people anytime and anywhere through a small square." Break down long sentences and simplify wording for clarity.

* Some sentences shift between past and present tense, which affects readability. Example: "This study presents the development and implementation of a novel gamified chatbot system that was tested in eight seminars."

* There are some missing or misused articles ("a," "an," "the").

Example: "Participants attended a health seminar once a week for eight weeks, which is two months." Suggested revision: "Participants attended a weekly health seminar for eight weeks."

Author Response

Dear Reviewer,
Thank you for your insightful and constructive feedback. We greatly appreciate the time and effort you devoted to reviewing our manuscript. In response to your comments, we have carefully revised the manuscript and addressed each point in detail. A point-by-point response outlining all changes is provided in the attached response document.

 

Best regards,

HanChun Huang

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This manuscript is an interesting attempt to present the use of AI for the educational purpose, i.e. aiming to conduct a public-health intervention. However, its scientific contribution and the quality of writing are very low, and do not meet the basic standards, required for publishing in an international journal.

While the Introduction might be more engaging and attractive to prospective readers, it serves the purpose of this study. Unfortunately, the rest of the paper is not acceptable. Section "2. Related Work" (aiming to serve as a literature review) starts with a snippet of text, taken directly from the MDPI paper template. Authors have simply forgot to delete it, which shows they have not read the manuscript before submission. In this section, there is some information about gamified chatbots, with the information on the technological state-of-the-art from the 2018-2021 period. This is, obviously, obsolete. There are almost no references about scientific studies, looking at the gamified learning experiences, tools and techniques, and no discussion, or references, in the context of using those in the public health context. Therefore, this section does not serve its purpose, and needs to be completely re-written.

In the Materials and Methods section, there is too much emphasis on the design of the gamified chatbot, including presentation of its user interface. This description is too extensive, and could be moved to the Supporting Information, if authors really believe it should be presented.

In addition, in this section we find out that the chatbot is AI-based, and there are no references to AI in this study's title, abstract, or the theoretical background. 

The entire statistical analysis presented in the Results section, is a single paired sample t-test. We are left to wonder what this results represents, how it connects to the extant literature, or what kind of theoretical contribution it represents. Unfortunately, there is no contribution to the theory, and no information about the context of the presented chatbot, no discussion of results in the light of the extant theory, and no relevant knowledge which can be generalized from this study.

Unfortunately, the paper is also almost impossible to amend, or revise, since a single t-test provides no opportunity for a more extensive analysis.

Author Response

Dear Reviewer,

Thank you for your time and effort in reviewing our manuscript. We appreciate your detailed feedback, which has provided us with valuable insights on how to improve our study. We have carefully considered your comments and have revised the manuscript accordingly. A point-by-point response outlining all changes is provided in the attached response document.

Sincerely,

HanChun Huang

 

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Dear Authors,

Thank you for submitting the revised version of your manuscript, "A Pilot Study on AI-Powered Gamified Chatbot with OMO Strategy for Enhancing Parental Nutrition Knowledge." I appreciate the effort you have made in addressing most of my previous concerns, and the study has improved as a result.

However, I noticed that many relevant studies published in Digital Journal have not been considered. To strengthen the theoretical foundation and ensure that your study builds on prior research in this context, I encourage you to incorporate insights from recent publications in the field. The following studies may be particularly useful:

1. https://doi.org/10.3390/digital5020009

2. https://doi.org/10.3390/digital5020010

Additionally, I observed that the reference list does not fully adhere to the formatting requirements of Digital Journal. Please ensure that all references follow the correct citation style as specified by the journal’s guidelines.

I appreciate your attention to these matters. 

Author Response

Dear Reviewer,

We sincerely thank you for your thoughtful and constructive feedback on our revised manuscript entitled “A Pilot Study on AI-Powered Gamified Chatbot with OMO Strategy for Enhancing Parental Nutrition Knowledge.” Your suggestions regarding the inclusion of additional literature from Digital Journal and proper formatting of references have been very helpful in strengthening our manuscript.

In response, we have carefully revised the manuscript by integrating the two suggested references (Rahman & Uddin, 2025; Patel et al., 2025) in the theoretical section, specifically addressing the relevance of AI models and mHealth adoption. Furthermore, we have thoroughly updated our reference list to fully comply with the journal's citation format.

A detailed, point-by-point response to your comments is attached with this letter. We truly appreciate your support in helping us improve the quality and academic rigor of our work.

Warm regards,


HanChun Huang

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The revised version of the manuscript meets the basic criteria for publishing a paper in an international research journal, which is a significant improvement, as compared to the first version, which has been submitted to this journal. However, the paper still needs to be improved, as there are two major issues to be resolved:

  • Please rename Section 2 from Related Work to Theoretical Background, and 2.1. from Gamified Chatbot to Gamification in Education. This section needs to be substantially expanded to show previous work and extant literature in the field. Since your system relies on AI, you should also cover the role of AI in gamification, which has not been done at all.
  • Implications for future research need to be separated from conclusions and included into the new section 5. Discussion (a separate section 6 Conclusion to be revised, as well). In the discussion, please position your contribution within the extant literature (referring to the theory in sections 2.1 and 2.2) and state your scientific contribution.

Good luck with you revisions.

Author Response

Dear Reviewer,

Thank you very much for your detailed and insightful feedback on our manuscript titled “A Pilot Study on AI-Powered Gamified Chatbot with OMO Strategy for Enhancing Parental Nutrition Knowledge.” We are grateful for your positive remarks and your helpful recommendations for improvement.

In response to your suggestions, we have implemented the following major revisions:

  1. We have renamed Section 2 to Theoretical Background and expanded it to include three subsections—Gamification in Education, The Role of AI in Gamification, and Online Merge Offline Model—thus providing a stronger theoretical foundation supported by updated references.

  2. We have restructured the manuscript to separate the Discussion and Conclusion sections. The Discussion now contextualizes our findings within the literature presented in Section 2 and outlines the scientific contribution and future research directions, while the Conclusion succinctly summarizes our results.

We believe these changes have significantly improved the quality and clarity of our study. Please find the detailed, point-by-point response to your comments attached with this letter.

With sincere appreciation,
HanChun Huang

Author Response File: Author Response.pdf

Round 3

Reviewer 2 Report

Comments and Suggestions for Authors

In its third revision, your paper is now publishable, as it has been significantly improved, as compared to the first submission. The major issue is a very small number of respondents, but this has been acknowledged in the manuscript.

For the final revision, please review and rewrite lines 284-332, 446-467 and 479-522, which might have been written by an AI tool (or, at least, sound like a more "robotic", AI-writing).

 

Author Response

Dear Reviewer,

We sincerely thank the reviewers and the editor for their thoughtful and constructive comments. We have carefully addressed all suggestions and made substantial revisions to improve the manuscript. In particular, we revised lines 284–332, 446–467, and 479–522, which were originally written in Traditional Chinese and translated into English. Recognizing that the original translation may have led to a tone that appeared mechanical or overly formal, we have rewritten these sections to ensure a more natural and academically appropriate style. We hope that the revised manuscript meets the expectations and standards of the journal.

Sincerely, 

HanChun Huang

Author Response File: Author Response.pdf

Back to TopTop