PONE-D-25-23239Enhanced Audience Sentiment Analysis in IoT-Integrated Metaverse Media CommunicationPLOS ONE

Dear Dr. Huang,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Aug 01 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Hung Thanh Bui, Ph.D

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match.

When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section.

4. Thank you for stating the following financial disclosure:

This research was funded by special research topic of cultural exchange of Ministry of Education (grant number CCIPE-YXSJ-20240060), key topics of open online course guidance for undergraduate universities in Guangdong Province (grant number 2022ZXKC361), and Guangzhou Musicians Association "Music Culture research" and "Primary and secondary school music education reform project" (grant number 24GZYX003).

Please state what role the funders took in the study. If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."

If this statement is not correct you must amend it as needed.

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf.

5. We note you have included a table to which you do not refer in the text of your manuscript. Please ensure that you refer to Table 3 in your text; if accepted, production will need this reference to link the reader to the Table.

6. We are unable to open your Supporting Information file [Main-Manuscript.tex]. Please kindly revise as necessary and re-upload.

Additional Editor Comments :

This paper presented a deep learning-based model integrating Bidirectional Encoder Representations from Transformers (BERT) with the Generative Pre-trained Transformer (GPT) for sentiment analysis. The authors did experiment on Twitter Sentiment140 and Amazon Reviews datasets and analyzed the result.

The authors should explain in detail why they used a method by integrating Bidirectional Encoder Representations from Transformers (BERT) with the Generative Pre-trained Transformer (GPT)?

They did 3 algorithms and 37 formulas, but they didn’t have any improvement on BERT and GPT, just combining all components together, it means that their framework processes and calculates all parts automatically, the authors only did on the result of some main parts. So they should present what their improvement is clearly.

They should explain how they chose all parameters in their experiments in detail

They compared with three methods; they should do more comparison with another latest studies.

Researching in NLP is going fast with many new techniques, they should refer advanced methods in recent year, for example in ACL, CL, EMNLP conferences...

Ablation study should be done on the paper.

They should show some best and worst results and analyze them in detail.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Partly

Reviewer #3: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: No

Reviewer #2: Yes

Reviewer #3: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: 1. Although performance improvements (e.g., ~5.8 percentage points in accuracy relative to the next best starting value) are significant, the lack of p-values or confidence intervals raises questions about whether these gains hold under repeated random starts.

2. The study indicates that combining BERT-based encoding and GPT-focused generative understanding produces effective results. However, there is no clear ablation study measuring the isolated contribution of each component. Although the overall results are good, a bit ablation study would strengthen the causal link between the hybrid architecture and performance gains.

3. The average accuracy (94.5%) and F1 score (91.5%) have been determined. However, standard deviations or confidence intervals have not been determined for multiple studies or folds. Without variability measurements, it is not possible to assess whether the observed gains are stable or whether they are due to random fluctuations between different data divisions.

4. The study compares BG-Hybrid with three basic lines (CBA-Evaluation, FER-Tracker, Emote-Twitch) and indicates the absolute differences. However, no McNemar test, matched preloading, or any hypothesis test was used to confirm that these differences did not occur by chance and were statistically significant.

5. An average inference latency of 250 ms is given. However, no information is provided about the variance, percentile breakdown (e.g., 95th percentile), or repeated measurements under different loads. For real-time systems, tail‐latency can be more critical information than the average.

Reviewer #2: This paper presents a deep learning-based model integrating Bidirectional Encoder Representations from Transformers (BERT) with the Generative Pre-trained Transformer (GPT) for sentiment analysis. This paper addresses very pertinent research problem. Following are some main points/suggestions based on the overall insight of the paper:

• The language of the manuscript should be improved significantly like typos, alignment, use of complex sentences like “This section details the system analysis of the sentiment analysis system we proposed 367 and gives an evaluation of its performance under several simulations”.

• There are lot of hyper parameters like a, b, and c in equation 27 but how did you choose their value, it should be discussed in detail?

• Perform the comparative analysis with the recent transformer-based deep learning approaches.

• There are too much mathematical equations. Equations 7, 8, 9, 10 and some others like these are very common concepts and there is no need to define them as equation.

• Please present confusion matrix of the prediction result.

• The multilingual capability of the model depends on the translation of text which will slow down the approach. Furthermore, accuracy will also depend on the accuracy of translation service. How this makes the presented model a generic multilingual approach.

Reviewer #3: The manuscript demonstrates notable ambition and technical effort, with well-documented implementation and thorough empirical testing. However, some improvements in clarity, methodological transparency, and contextualization within prior literature are essential for publication readiness.

1. While the manuscript demonstrates commendable technical depth, the volume of equations appears excessive for the applied nature of the study. Many of the mathematical formulations—particularly those related to stream segmentation, feedback adjustment, and sentiment scoring—restate established concepts without clear empirical justification or practical interpretation. This level of formalism risks overshadowing the real-world applicability of the proposed system. A more balanced approach would involve streamlining the mathematical content and focusing instead on how the system operates in practice, its deployment challenges, and its impact in real-time IoT-Metaverse scenarios. Reducing equation density and emphasizing applied insights would improve clarity and better align the paper with its intended audience.

2. The manuscript often uses overly dense or jargon-heavy phrasing (e.g., “contextual sentiment score SCk,” “temporal segmentation strategy dynamically adapting to data stream velocities”), which impairs readability. Simplifying sentence structure without losing technical depth would improve accessibility.

Several sections (e.g., discussion of modules, performance comparisons) repeat similar points with only slight variation. This could be condensed to enhance flow.

3. From the model implementation perspective, although equations are thoroughly included, key architectural specifics of the BG-Hybrid model (e.g., the number of layers, embedding size, and fusion method between BERT and GPT outputs) are missing. Add a table of model hyperparameters and implementation details. Clarify how weights and feedback mechanisms are operationalized and validated.

4. The related work section is extensive but lacks critical engagement. It reads more like a catalog of previous studies, which is usually the conventional way of writing technical papers. However, this section can benefit from a serious analytical synthesis. Recent advancements in sentiment analysis, including those utilizing transformer ensembles, knowledge-aware modeling, and multilingual domain adaptation, are either absent or lightly addressed. Highlight specifically how the BG-Hybrid model differs from or improves upon models like RoBERTa, XLNet, or other BERT-GPT fusion attempts. Discuss cross-lingual and cross-modal sentiment analysis literature for broader grounding.

5. While the performance benchmarks are impressive, there is no ablation study showing the contribution of individual components (e.g., BERT-only vs. BG-Hybrid, effect of feedback module, effect of adaptive windowing). Include at least an additional baseline comparison (e.g., fine-tuned RoBERTa, XLNet, or DistilBERT). Justify the baseline choices.

Overall, this manuscript presents a promising and well-structured sentiment analysis framework suited for real-time, heterogeneous data environments like the IoT-enabled Metaverse. The hybrid deep learning architecture and its integration with feedback-driven adaptation are notable strengths. However, to meet the publication standards, the following are essential:

• Improve clarity and reduce redundancy

• Expand on methodological transparency

• Deepen engagement with related literature

• Add comparisons to more competitive baselines

• Less theoretical and more practical outlook

With these revisions, the paper would make a valuable contribution to the field of AI-driven media sentiment analysis in complex, connected environments.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: Yes: Fatima Habib

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

Enhanced Audience Sentiment Analysis in IoT-Integrated Metaverse Media Communication

PONE-D-25-23239R1

Dear Dr. Huang,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Hung Thanh Bui, Ph.D

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

All comments are addressed.

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

Reviewer #3: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: (No Response)

Reviewer #3: (No Response)

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: (No Response)

Reviewer #3: (No Response)

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: (No Response)

Reviewer #3: (No Response)

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: (No Response)

Reviewer #3: (No Response)

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: The authors have responded satisfactorily to my comments and made the necessary additions and corrections.

Reviewer #3: (No Response)

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #3: Yes: Fatima Habib

**********