All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Based on the reviewer comments, the manuscript can be accepted.
[# PeerJ Staff Note - this decision was reviewed and approved by Xiangjie Kong, a PeerJ Section Editor covering this Section #]
The authors addressed the given suggestions and comments.
N/A
N/A
N/A
All the comments are well-revised. I would be happy to suggest the acceptance of the article.
NIL
NIL
Based on the reviewer comments, the manuscript must be revised.
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** PeerJ staff have identified that the English language needs to be improved. When you prepare your next revision, please either (i) have a colleague who is proficient in English and familiar with the subject matter review your manuscript, or (ii) contact a professional editing service to review your manuscript. PeerJ can provide language editing services - you can contact us at copyediting@peerj.com for pricing (be sure to provide your manuscript number and title). – PeerJ Staff
The paper provides a thorough literature review on facial expression recognition (FER), covering historical advancements, current technologies, and future directions. This extensive review is beneficial for readers unfamiliar with the field.
The manuscript is well-organized, with distinct sections for introduction, methodology, findings, and future directions.
N/A
Based on the review, the paper is not yet acceptable for publication in its current form. It is recommended that the authors address the areas for improvement, particularly by clarifying their novel contributions to the field, detailing their methodology more rigorously, and providing a deeper analysis of their findings.
1. The paper should articulate its unique contributions more clearly. Are there new methodologies, frameworks, or insights presented? If so, these need to be highlighted and differentiated from existing work. This is vital for the paper to stand out in a crowded field.
2. A more detailed explanation of the systematic literature review process is necessary. This includes the criteria for including and excluding studies, databases searched, keywords used, and the process for analyzing the selected articles. Such transparency ensures the review's reproducibility and credibility.
3. The paper should analyse identified future directions and challenges more deeply. Rather than merely listing these, it should explore their implications for the field, potential solutions to challenges, and specific areas where future research could make significant contributions.
4. Incorporating detailed technical descriptions or case studies would significantly enhance the paper. This could involve explaining specific technologies, algorithms, or models used in FER, real-world applications, or significant studies' outcomes. Such examples help bridge theory and practice, making the paper more informative and engaging for readers.
5. References should be updated. No reference to 2024 is present.
Addressing these areas thoroughly would strengthen the paper substantially.
## English language
Language used in the text is clear.
## Intro, background and references
Needs to be refined. There are claims that stand unconvincing, like:
> It has been utilized in various fields, including security and surveillance, law enforcement, education, health and safety, advertising and marketing, finance and banking, access control, transportation, attendance tracking, entertainment and gaming, and many more.
In most of the above applications, facial recognition is adopted, not facial expression recognition.
Facial expression recognition and emotions recognition are two different thing, and we have to be extremely careful. Emotions are a research filed of psychology.
## Text structure
Needs to be reworked. Contains too much short sections, composed by two-three sentences.
## Figures and tables
Figures are visually clear. Figures 2, 4, and 5 would have been good graphical illustration if the text was intended for popular audience, not for a scientific journal.
## Formal results
There are no clear definitions or theorems. No detailed proofs.
The paper is a literature survey. There is no scientific research in the text. The survey contains a description of the methods that just scratches the surface of the topic. There is no real and deep method description and comparison.
The survey does not go deep into the scientific details of mentioned methods.
In this paper, the authors have discussed the basics of Facial Expression Recognition (FER) and architectural elements, FER applications, FER-based global leading companies, the interconnection between FER, Internet of Things (IoT), and Cloud computing, summarized open challenges in-depth to FER technologies, and provided future directions.
In the end, the conclusion and future thoughts are discussed. By overcoming the identified challenges and future directions in this research study, researchers will revolutionize the discipline of facial expression recognition in the future.
However, I have some major concerns before the acceptance of the article.
First, why did the authors give priority to Kitchenham for the systematic process instead of PRISMA, which is more flexible for SLRs?
Why did the authors ignore Scopus and Web of Science, which are more systematic in searching?
Search strings are missing, which are crucial in any systematic review. I suggest a table of search strings with mapping of PICO elements for each question.
Why are results missing for the review process?
Results based on venues, years, and other crucial parameters are very important for any review.
Diagram specifically Figure 1 is not well-formulated; I suggest formal diagrams of Kitchenham to be drawn.
There are multiple problems with this SLR including results, discussion in details, search methodology weaknesses, etc. The paper needs major revisions in its methodology.
Included in basic reporting.
Included in basic reporting.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.