Review of Studies on Emotion Recognition and Judgment Based on Physiological Signals

Round 1

Reviewer 1 Report

The article presents a review of technologies for automatic recognition of human emotions based on the analysis of physiological signals such as EEG, EDA, ECG, EMG and other multimodal signals. The authors introduce and describe the main definitions related to this field and highlight the various emotion recognition approaches. However, there are sections that need improvement to make the article more comprehensive and informative.

1) The authors need to provide more clarity and evidence to support the statement that physiological signals are better indicators of a person's emotional state than facial expressions or voice. To further strengthen this argument, they can provide the top 3 best results on the AffectNet corpus (Emotion-GCN - https://paperswithcode.com/paper/exploiting-emotional-dependencies-with-graph, EmoAffectNet - https://paperswithcode.com /paper/in-search-of-a-robust-facial-expressions, Multi-task EfficientNet-B2 - https://paperswithcode.com/paper/classifying-emotions-and-engagement-in-online) and describe the work of other modalities. See more: https://paperswithcode.com/sota/facial-expression-recognition-on-affectnet.

2) The article needs to be updated with the latest works of the scientific community, specifically works presented at conferences focused on physiological signals.

3) A summary table should be included to organize and present the information in a more structured and concise manner.

4) The article would benefit from the addition of more examples and illustrations in vector format.

5) The current illustrations should also be presented in vector format.

6) The abstract should be expanded to provide a better overview of the article.

7) The keywords should also be expanded to improve the searchability of the article.

8) The conclusion should be updated to reflect the expanded review article and take into account the previous remarks.

9) It is unclear if there are any methods or datasets for experiments, and this information should be presented in the form of a table.

10) Finally, it would be useful to include a section that specifically addresses the ethical and privacy concerns related to the use of physiological signals for emotion recognition. This could include a discussion of the need for secure and transparent data storage, protection of sensitive information, and the possibility of misuse or discrimination based on emotional state.

Overall, these additions will improve the quality and comprehensiveness of the review article. The topic is relevant, and there are many works that can be compared and evaluated for their strengths and weaknesses.

Author Response

See attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Dear Authors,

Please find the attached file for your reference. Please update the paper based on the comments and resubmit it.

Regards  

Comments for author File: Comments.pdf

Author Response

See attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

The article addresses a review of studies on the emotion recognition and judgment based on physiological signals.

1- The abstract should be modified. There is not enough information about the methodology, proposed works, conclusion y comparison with other works in this part. Also, the abstract can be rewritten longer but with more details and some numerical results.

I suggest you structure your abstract as presented in https://www.principiae.be/pdfs/UGent-X-003-slideshow.pdf

2- The introduction has been written short and it should be extended to new published papers for recent years. In the introduction should be expressed the better state-of-art of new methods. The new references will also be examined in this part. I would like to see the articles for last and this year in this section.

3- There are many paragraphs in the introduction, where more of them can be merged to have better structure.

4- Since the article is a review, it needs a better state-of-the-art, where there are many works related to this topic during last years, where had not been mentioned in this article.

5- I cannot see the details of the methods in this article. The methods were explained very short without preparing enough explanation.

6- Figure 2 should be explained in a better way. There are some details, which have not been explained in the article.

7- Simulation conditions are not well discussed. The approaches were illustrated only on some specific cases, which is not enough to draw a complete and accurate conclusion about the methods.

8- As a review paper, the presented methods seem separated, and it needs much better connections between introduced algorithms.

9- Please, do not forget that the clarity and the good structure of an article are important factors in the review decision. Please read the paper carefully (again) and correct it in English.

Author Response

See attachment.

Author Response File: Author Response.docx

Reviewer 4 Report

It is a valuable review of the possibilities of detecting human emotions based on physiological signals. The conclusions drawn by the authors on the basis of the literature review are accurate.

Author Response

See attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

The authors have made significant improvements to the article, making it useful and of interest to many specialists. The only recommendation is for Figures 1 and 3 to be presented in vector format, for example, using the service https://app.diagrams.net/ or similar. Additionally, Tables 1 and 2 should not be presented as figures but as regular tables.

Author Response

See attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Dear Authors,

Thank you for addressing all my comments and I don't have any further concerns on the paper.

Regards 

Author Response

See attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

- The quality of all figures are very low. They have to be changed with high quality figures.

- Tables seem as figures with low quality. The authors always should plot table with making picture in any other side.

- still I can not see any systematic and correct comparison between reported methods in this review article.

- The review article should be organized in a better structure with all detials.

Author Response

See attachment.

Author Response File: Author Response.docx