A Review of Multimodal Interaction in Remote Education: Technologies, Applications, and Challenges

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

It is a very interesting paper, on a relevant topic, and very well written in general terms. It deserves publication but only after addressing the following criticism. 

In my opinion, the paper does not transmit a clear message about its content. For instance, the title suggests (at least to this referee) that the paper deals with a  novel proposal about  how to enhance remote education through multimodal interaction. But it is not so. As I understand it,  after reading some other parts of the paper, the paper goal is to “review” some bibliographic references dealing with the use of multimodal interaction on remote education. 

Indeed, in the  Abstract it is declared:  “ This review provides insights into the evolving landscape of multimodal interaction in remote education, paving the way for more intelligent, adaptive, and inclusive learning environments. “

But at the  end of section 1 it is declared: “This paper explores how multimodal interaction technology is used in remote education, focusing on data collection and evaluation.” Thus, again, there is no reference at all to the fact that the paper is essentially a review. 

Thus, I think  it should make more precise that the “exploration” is done by “reviewing” a collection of bibliographic references, not by other means (for example, by directly collecting data from academic authorities in diverse countries,  or by  asking teachers to answer a questionnaire, etc..).

Also, at the Conclusions, this sentence “This research investigates the impact of multimodal technology on remote education….The results suggest…”  does not make clear that the “investigation” was limited to screeening  out “… 25 research articles on multimodal interaction technology…,”. (Section 4, first paragraph). 

How were these 25 research articles chosen? Why are they representatives of the state of the art? Do they include enough data for all educational levels? Why the obtained data from the 25 articles is enough for deriving the conclusions?

In summary: The goal, content and methodology adopted in the paper for the investigation should be clearly, more completely described and justified,  in an earlier section of the paper.

Author Response

Please see the attachment.

Author Response File: Reply to Reviewer 1

Reviewer 2 Report

Comments and Suggestions for Authors

I would firstly like to start by congratulating the authors on their work on building up the article entitled Enhancing Remote Education Through Multimodal Interaction: Technologies, Applications, and Challenges. The topic is very relevant and important, and, by title, it addresses a multidisciplinary approach.

The article is in good shape, however, to get published in MDPI it should be slightly enriched. Below are a few points to do so but the authors are free to seek more around them… I will only focus on how to strengthen the research.

• The paper is providing a broad review of the multimodal interaction; however, it does not identify any specific research gap – a gap that the paper could attempt to fill therefore the authors are advised to provide an empirical validation of the experiments if possible.
• In light with the above, the literature review is broad and should be more targeted – maybe focusing on specific tech or pedagogical innovations to start differentiate the current study from the previous.
• Limitation of the multimodal systems that are presented in the paper are also needed in order to provide a better solution – as the paper aims doing in the title and abstract.
• Following the above, a table comparing the existing studies would help.
• Also they should take in consideration the fact that they are only relying on controlled environment studies – that might turn to be a bias (maybe addressing this as a limitation will help).
• The research hypothesis (as identified in lines 65-70) could be enounced explicitly in a dedicated subsection of the introduction and refined to focus on specific set of multimodal technologies (a research question example could be: What specific multimodal interaction techniques most effectively enhance student engagement and learning outcomes in remote education? and/or How does multimodal learning analytics improve student outcomes compared to traditional online learning systems?)
• Including case studies or experimental results will help improving the scientific soundness of the paper – maybe some in which the authors will compare new approaches in learning with online / traditional ones.
• While the data presented in sections 2 (especially 2.2 and 2.3) and 3 is relevant to the current technologies in use, the paper lacks in providing a structured methodology (especially as it poses as an experimental study). How the technology presented were chosen and why – if there are any notable frameworks used for the research, it should be mentioned.
• The paper mentions data collection, but it should give more specific details on how it is used in education, which data sources and some other relevant details.
• In line with the previous comment, even though the paper mention tech challenges, it does not provide a clear methodological solution – that should be addressed in a clear scientific way.
• The discussion and conclusions are aligned generally with the arguments, but they are not supported by empirical validation – as the paper tries to do. They should demonstrate the potential of multimodal interaction in a strong and undisputed way.
• Also, in conclusion the authors should raise some challenges of the new technologies for the educational environment.
• Here also answering explicitly to the research question or hypotheses (or aims – depends how the authors are willing to express that), is needed.
• In the conclusion section authors are recommended to add a subsection with future research.
• References are up to date however, there is a strong need to bring some empirical studies up from the scientific literature and/or cross studies that compared learning approaches to date.
• The figures / charts provided in the article give a visual representation of the study. However, a flowchart of the multimodal interaction in remote education would bring more light to the study – providing the authors will follow the comments above.

By addressing the above, the article will fit the expectation of MDPI.

Author Response

Please see the attachment.Reply to Reviewer 2