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.
Dear authors, we are pleased to verify that you meet the reviewer's valuable feedback to improve your research.
Thank you for considering PeerJ Computer Science and submitting your work.
[# PeerJ Staff Note - this decision was reviewed and approved by Arkaitz Zubiaga , a 'PeerJ Computer Science' Section Editor covering this Section #]
I'm fine with the current version and it's suitable for publication
I'm fine with the current version and it's suitable for publication
I'm fine with the current version and it's suitable for publication
I'm fine with the current version and it's suitable for publication
Professional English is used throughout, and it is clear and easy to understand.
Original primary research is within the aim and scope of the journal.
Well-defined, relevant, and meaningful research question. Research fills knowledge gaps.
A thorough investigation is done ethically and technically.
Methods are detailed enough to replicate.
Impact and novelty are assessed properly. The rationale & benefit of literature are clearly stated.
All underlying data have been provided; they are robust, statistically sound, & controlled.
Conclusions are well stated, linked to the original research question, & limited to supporting results.
Thank you for your attention to my comments. I like your manuscript changes and response to my comments.
Dear authors,
You are advised to critically respond to all comments point by point when preparing a new version of the manuscript and while preparing for the rebuttal letter. Please address all the comments/suggestions provided by the reviewers.
Kind regards,
PCoelho
**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 [email protected] for pricing (be sure to provide your manuscript number and title). – PeerJ Staff
The paper is clear. It presents an extensive literature review.
The authors have well explained the aim of the paper, the data collection method, the methodologies employed. The theory is correctly addressed.
The tables and figures are well described, but maybe the captions are too long.
Data are shared.
The experimental design is interesting addressing an important problem related to sentiment analysis during classes of a particular type of students, the low vision ones.
The researchers perform meaningful findings trying to solve an interesting research question.
The findings are clearly stated and its novelty is well expressed.
The manuscript uses terminology accurately, but should include definitional sections for terms such as "VADER", "SVM", and "CNN", which are important for understanding the research but are not familiar to all journal readers.
The manuscript adequately cites previous research, but some of the statements are too broad and could be strengthened by specific research. For example, the section on advances in sentiment analysis in education (lines 104-116) could be strongly supported by references to recent meta-analyses or systematic reviews.
The introduction section could be expanded to include a discussion of previous approaches to sentiment analysis used specifically for visually impaired students, highlighting the new contributions made in this paper.
Some of the figures and tables lack comprehensive captions and explanations and are difficult to understand without context. Each figure and table should have a descriptive title detailing what is shown and discussing its relevance.
The manuscript is original research; however, it needs to clearly state how this fits within the broader aims and scope of the journal. A brief comparison with similar studies, perhaps in a different but related field, could highlight the novelty more effectively.Expand on the implications of this research beyond the academic performance of visually impaired students to include potential applications in other types of educational settings or learning models.
The description of the methods is detailed but should include specifics about the data preprocessing steps, model parameters, and any software or tool versions used. This will aid in true replicability.
no comment
Many figures and tables in the manuscript are densely packed with information, which can be overwhelming at first glance. It's importance to enhance the resolution and ensure that all text within these figures is easily legible. Consider using clearer, larger fonts and more distinct color contrasts to help readers understand your visual aids without straining.
Every figure and table must be thoroughly referenced within the main text. This not only guides the reader through your document but also contextualizes the visuals, making your arguments stronger and more persuasive. Make sure that each visual element is discussed in the text to provide a narrative bridge between your textual analysis and the data presented graphically.
The current manuscript would greatly benefit from the inclusion of supplementary materials. Providing access to the full datasets used, detailed configurations of your models, and any scripts or code repositories will enhance the transparency and reproducibility of your work. This is especially important in computational studies where the exact parameters and processing steps can significantly influence the results.
Alongside raw data and scripts, consider adding a supplementary file with a detailed methodology section or a tutorial. This should include step-by-step instructions on replicating your analysis, which can be particularly useful for students or researchers new to this field.
Your study introduces an innovative model for sentiment analysis, but how does it stack up against existing methods? A detailed comparative analysis would strengthen your manuscript. Highlight the specific advancements your method offers over previous techniques, such as increased accuracy, faster processing times, or better scalability. Use a side-by-side comparison with benchmarks from established methods to clearly present these improvements.
Include charts or tables that directly compare the performance metrics (like accuracy, sensitivity, specificity) of your model against those of traditional models used in similar contexts. This not only underscores the effectiveness of your approach but also helps in illustrating the practical benefits and potential limitations.
Discuss the limitations in the generalizability of your model more comprehensively. Are there specific types of impairment or educational contexts where the model might not perform as well? Addressing these questions not only helps in setting realistic expectations for your work but also in pinpointing areas for improvement.
The current study provides a snapshot of the benefits offered by your model. Future research could explore these effects over longer periods through longitudinal studies, which would help in understanding how consistent and reliable the model is in different phases of learning and across diverse student populations.
While your manuscript makes several claims about the effectiveness of the proposed system, these need to be backed by more comprehensive statistical evidence. For instance, correlate specific features of your sentiment analysis system, such as the emotional granularity it can detect, with improvements in learning outcomes.
The research paper presents an innovative approach to enhancing the educational experience of visually impaired students through sentiment analysis of their audio feedback in virtual learning environments. The study develops an intelligent model capable of categorizing sentiment responses into five distinct groups, aiming to provide educators with deeper insights into the emotional states of visually impaired students during online learning. By utilizing data from educational platforms, such as Microsoft Teams, during the COVID-19 pandemic, the model offers automated evaluation and visualization of audio feedback to support student performance.
The paper is generally well-written, with clear and concise language. However, attention to detail is needed to ensure consistency in terminology and clarity in expression. Additionally, efforts should be made to avoid jargon and technical language that may hinder comprehension for non-specialist readers. Overall, the language and grammar are proficient, but minor revisions could enhance readability and accessibility.
Specifically, the paper maintains a high standard of professional English, ensuring clarity and precision in communication. Adequate literature references establish a solid foundation in the field, providing essential context for the study. The article's structure, including figures and tables, is professionally executed, enhancing readability and comprehension. However, the use of figure format for the STT subsystem pseudocode is problematic. The study is self-contained, delivering pertinent results aligned with the research hypotheses. While the formal results are presented, there's room for improvement in providing clearer definitions of terms and theorems, along with more detailed proofs.
The study employs a rigorous methodology, leveraging SVM and ANN algorithms to predict and analyze students' sentiment responses and academic performance. The use of machine learning techniques, such as CNN, SVM, and ANN, demonstrates a sophisticated approach to sentiment analysis in educational settings. The paper is well-structured, with clear sections outlining the problem statement, methodology, results, and implications. However, the decision to present the STT subsystem pseudocode in picture format rather than text or tabular form raises concerns about transparency and reproducibility. Additionally, while the overall organization is effective, some sections could benefit from further elaboration to enhance clarity and coherence.
The research falls within the aims and scope of PeerJ Computer Science, presenting original primary research relevant to its field. The research question is clearly defined, relevant, and meaningful, addressing an identified knowledge gap in the field. The investigation maintains a high standard of rigor, both technically and ethically, ensuring the validity and reliability of the findings. The methods are sufficiently described, providing the necessary detail and information for replication and enhancing the study's transparency and reproducibility.
The omission of the STT subsystem pseudocode in text or tabular form is particularly concerning as it hampers the reproducibility and transparency of the study, undermining the credibility of the findings. Addressing this limitation is crucial to ensuring the integrity and reliability of the research. Furthermore, while the focus on visually impaired students is commendable, future studies should strive to encompass a broader spectrum of students with diverse learning needs to promote inclusivity and equity in education. Additionally, addressing the potential variability in model efficacy across different educational contexts would enhance the generalizability and applicability of the findings.
The impact and novelty of the research are not assessed, but meaningful replication is encouraged with clear rationale and benefits to the literature. All underlying data provided are robust, statistically sound, and controlled, ensuring the reliability of the study's findings. The conclusions are clearly stated, directly linked to the original research question, and appropriately limited to supporting the results obtained.
While the study offers valuable insights, several limitations warrant consideration. Firstly, the paper lacks transparency regarding the STT subsystem pseudocode, which is presented in a picture format rather than as text or in tabular form. This omission undermines the reproducibility and comprehensibility of the study, potentially hindering future research in this area. Additionally, the research primarily focuses on visually impaired students, potentially neglecting the broader spectrum of students with diverse learning needs. Furthermore, the efficacy of the model may vary depending on the quality and quantity of available data, which could limit its generalizability across different educational contexts.
Dear Author,
I have had the opportunity to thoroughly review your manuscript titled Development of an Intelligent Model for Sentiment Analysis of Visually Impaired Students' Audio Feedback in Virtual Learning Environments.
I commend you on undertaking research in such a vital area of educational technology and accessibility. Your study addresses a significant gap in the literature by proposing an innovative intelligent model designed to predict and analyze visually impaired students' sentiment responses through audio feedback in virtual learning environments. This model, which categorizes sentiments into five distinct groups, has the potential to offer valuable insights into the unique needs of visually impaired students and enhance their learning experiences.
However, I have identified several areas that require further clarification and improvement before the manuscript can be considered suitable for publication:
1. Presentation of STT Subsystem Pseudocode: The decision to present the STT subsystem pseudocode in a figure/picture format is unconventional and may hinder reproducibility. I recommend presenting this information in text or tabular form for clarity and accessibility.
2. Focus on Specific Student Demographics: While your study focuses on visually impaired students, it is essential to consider the broader spectrum of students with diverse needs and disabilities. Expanding the scope to include a more diverse student demographic would enhance the generalizability and inclusivity of your findings.
3. Potential Variability in Model Efficacy: While you highlight the efficacy of your proposed model in predicting academic performance, it is crucial to acknowledge the potential variability in model performance across different educational contexts. Providing insights into the factors influencing model efficacy and generalizability would strengthen the impact of your study.
In light of these concerns, I recommend that you carefully address the identified limitations and consider revising the manuscript accordingly. I encourage you to carefully consider the feedback provided and revise the manuscript accordingly. Once the revisions have been completed, I would be happy to reevaluate the manuscript for further consideration.
Thank you for your attention to these comments, and I look forward to seeing the revised version of your manuscript.
Sincerely
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.