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.
I am pleased to accept the paper. The topic is interesting for the readers and we can hope for a good discussion around the topic.
[# PeerJ Staff Note - this decision was reviewed and approved by Rong Qu, a PeerJ Computer Science Section Editor covering this Section #]
Both the reviewers have identified that minor revisions are required. The authors are advised to carefully address the comments. For example, both the reviewers have identified that some of the figures are redundant and can be removed. Both the reviewers have mentioned that there is a need for English proofreading.
Overall, I am satisfied with the authors' response.
There is still room for some English editing of some of the sentences.
I have no further comments
There is still room for modification of the discussion and conclusion. The conclusion is still part of the discussion and not setting the ground for further research or implications of the current study findings.
I agree with reviewer 2 that the figures about each app are not needed in the manuscript especially that the focus is on the model and not just the results of the sentiment analysis. They are mostly repetitive and show similar results. The results can be summarize in the text and refer to an Appendix that contains al the figures.
no comment
More explanation is needed for Figures 6–12. The size of the paper can be reduced by grouping the Figures.
no comment
- Take off the title "Discussion," the body paragraphs have sufficient detail.
- Add details (step by step) to the algorithms
We have now received comments from the reviewers. Both the reviewers agree that the work can bring value. However, there are certain aspects that can be improved. Hence, we are making a decision for revision of the manuscript. The decision is based on the reviews received from the reviewers.
I thank the authors for a meticulous clear layout of the introduction and discussion. The background sets the field for the research in question. It highlights the need for the need of a new method of sentiment analysis. I believe this is the focus of the manuscript rather than the mere results of the review of the online apps.
I believe the research question could be improved to highlight the values of this research as a new way of analysis. A secondary outcome is the actual results of the online app reviews. I believe this manuscript is more powerful for other researchers who work in data analysis, and machine learning rather than researchers who work in the social behavioral field.
The authors have provided an adequate analysis of the comparison of the proposed new method as compared to other models.
The conclusion is very concise and the authors could elaborate more.
All of the comments and suggestions are available in the additional comments section.
no comment
no comment
The idea of self-voting classification is proposed in this paper, in which multiple variants of the same model are trained using alternative feature extraction methodologies, and the final prediction is based on the ensemble of these variants. The authors attempted to deliver a good study, however I have the following issues about accepting it in its current form for publication.
> The abstract and introduction are well written, and the contributions are briefly summarised in the introduction as well. Describe briefly the research's significance.
> The text is repeated and reused in several areas of the paper, and I suggest that the duplicate text be removed.
> In the methodology, describe the model explicitly. Detailed description is required about the data.
> I would advise against describing the procedures employed. The authors should explain how and why they employed the existing methodologies. I noticed this in both the pre-processing and prior portions.
> Already known equations are utilised throughout the paper to demonstrate how the suggested methodology works, although I oppose presenting them in this paper. Authors should concentrate on their model.
> Try to decrease the number of figures in the result section; if the behaviour of the figures is nearly same, authors can merge them.
> At the end of the result section, provide a genuine discussion.
> The true conclusion of the paper should be provided by the authors. The majority of the conclusion is currently a summary of the paper.
> Authors can present their framework using a flowchart or algorithm, with less emphasis on existing methodologies.
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.