Please submit your revised manuscript by Sep 29 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.. 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.. 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.. 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.

• 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 . 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 . 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 . 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,

Biljana Gjoneska

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. In your Methods section, please include additional information about your dataset and ensure that you have included a statement specifying whether the collection and analysis method complied with the terms and conditions for the source of the data.

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. We note that Figure 2, Figure 3, Figure 7 and Figure 8 in your submission contain map images which may be copyrighted. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For these reasons, we cannot publish previously copyrighted maps or satellite images created using proprietary data, such as Google software (Google Maps, Street View, and Earth). For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright.

We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission:

1. You may seek permission from the original copyright holder of Figure 2, Figure 3, Figure 7 and Figure 8 to publish the content specifically under the CC BY 4.0 license.

We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text:

“I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.”

Please upload the completed Content Permission Form or other proof of granted permissions as an "Other" file with your submission.

In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].

2. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only.

The following resources for replacing copyrighted map figures may be helpful:

USGS National Map Viewer (public domain): http://viewer.nationalmap.gov/viewer/

The Gateway to Astronaut Photography of Earth (public domain): http://eol.jsc.nasa.gov/sseop/clickmap/

Maps at the CIA (public domain): https://www.cia.gov/library/publications/the-world-factbook/index.html and https://www.cia.gov/library/publications/cia-maps-publications/index.html

NASA Earth Observatory (public domain): http://earthobservatory.nasa.gov/

Landsat: http://landsat.visibleearth.nasa.gov/

USGS EROS (Earth Resources Observatory and Science (EROS) Center) (public domain): http://eros.usgs.gov/#

Natural Earth (public domain): http://www.naturalearthdata.com/

5. For studies involving third-party data, we encourage authors to share any data specific to their analyses that they can legally distribute. PLOS recognizes, however, that authors may be using third-party data they do not have the rights to share. When third-party data cannot be publicly shared, authors must provide all information necessary for interested researchers to apply to gain access to the data. (https://journals.plos.org/plosone/s/data-availability#loc-acceptable-data-access-restrictions)

For any third-party data that the authors cannot legally distribute, they should include the following information in their Data Availability Statement upon submission:

1) A description of the data set and the third-party source

2) If applicable, verification of permission to use the data set

3) Confirmation of whether the authors received any special privileges in accessing the data that other researchers would not have

4) All necessary contact information others would need to apply to gain access to the data

6. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Additional Editor Comments:

Esteemed Authors,

Thank you for your patience with the prolonged review process. Your understanding for our voluntary services (aimed entirely for the advancement of the academic community and the science) is much appreciated indeed.

I have finally received the reports from two reviewers with differing areas of research interest (Computer Science and Psychology) but complementary and converging assessments. I am pleased to report that both reviewers find some merit in your work titled "Regional and temporal patterns of partisan polarization during the COVID-19 pandemic in the United States and Canada" (ID: PONE-D-25-11475), highlighting that the study is "relevant, interesting and insightful" (Rev 1), as well as "timely and methodologically innovative" (Rev 2). However, both reviewers also identify some major shortcomings, and are unified in their observation that the study is pending major revision before even being considered for proceeding further. The manuscript requires rework in all major areas as follows:

- The introductory part requires better positioning of your study within the existing scholarly literature on the topic, especially with respect to existing LLMs exploring similar subjects (as pointed out by Rev 1), and with respect to the political and temporal context (as pointed by Rev 2).

- The methodological part should be strengthened by including rationale for the method of choice (text similarity) and comparisons with other network-based approaches (as pointed out by Rev 1), as well as clarification (definitions, formal criteria for evaluation) of some of the investigated variables like conspiracy theories and sentiment analysis (as pointed out by Rev 2).

- The results require major rework of nearly all figures that are of unacceptable low quality. Take for example the opening illustration (Fig.1) which offers conceptual design of the study as a way to orient the reader, but it is so overloaded and busy, that the effect is completely the opposite (so it better be excluded). With respect to the rest of the figures, please take care to address all issues raised by Rev 1 as regards this.

- The limitations should include acknowledgments (justifications) of the temporal differences in the period of data collection vs period of vaccination, as well as note of the observations made by Rev 2.

Overall, this is rather ambitious undertake (examining phenomena across large data and populations, embedded in complex political and cultural contexts), that might easily collapse under "its own weight" of going in many different directions but (possibly) leading nowhere outside the expected conclusions (as regards the polarization across party lines that is more pronounced in US than Canada, and more pronounced for RW than LW partisans). This is a tangible risk if the work is not clearly directed, carefully guided and very focused, and written in a corresponding manner. With respect to the language, Rev 2 objects the use of the frequent evaluative language, which should be replaced with informative, concrete and language that is supported by facts.

The reviewers have also identified some more specific issues and carefully listed them in their reports. Please make every effort to address each issue with sufficient quality and in sufficient manner. Also, please note that the revised manuscript might still be considered not finalized or even acceptable for publication, as some additional issues might arise during the next round of revisions by the same or a new set of reviewers (depending on their availability).

With this I conclude my message and send best regards for productive revision of your manuscript.

Sincerely,

Biljana Gjoneska

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

Reviewer's Responses to Questions

Comments to the Author

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

Reviewer #1: Yes

Reviewer #2: Partly

**********

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

Reviewer #1: Yes

Reviewer #2: I Don't Know

**********

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.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

Reviewer #2: Yes

**********

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

Reviewer #1: Yes

Reviewer #2: Yes

**********

Reviewer #1: This manuscript presents a computational study of online partisan polarization during the COVID-19 pandemic in the U.S. and Canada. Analyzing over 50 million tweets, the authors propose using language model embeddings to measure polarization across regions and time. The findings show stronger polarization in conservative areas—especially in the U.S. The study is relevant, interesting, and insightful. However, the paper could have been organized better, positioned more precisely in the literature, written more clearly, and the figures should have been better for an appropriate evaluation.

My two major concerns are:

- As the authors have noted, the approach relies on text similarity rather than explicit stance or relational structure. Embedding-based measures can miss key contextual cues such as sarcasm, negation, or indirect disagreement. On the other hand, there are other approaches based on investigating the network of user interactions, which may be more insightful as it can consider the actual flow of information. The authors should at least provide a comparison of the benefits and drawbacks of their approach compared to network-based approaches. One study that explores polarization surrounding vaccination discussions on Twitter is given in Cinelli et al., 2021.

> Cinelli, M., De Francisci Morales, G., Galeazzi, A., Quattrociocchi, W., & Starnini, M. (2021). The echo chamber effect on social media. Proceedings of the national academy of sciences, 118(9), e2023301118.

- The authors have presented their approach as novel, but having in mind that language models have been around for a long time now, I think that there have already been other similar applications, such as the one from He et al., 2021, so I think the authors should better position their work in the literature.

> He, Z., Mokhberian, N., Câmara, A., Abeliuk, A., & Lerman, K. (2021). Detecting polarized topics using partisanship-aware contextualized topic embeddings. arXiv preprint arXiv:2104.07814.

My other remarks are:

- Line 108: As I understand, these data-filtering keywords are different from the topic-specific keywords discussed later, so the authors should consider renaming them.

- Line 120: The authors should comment how do they believe the time difference between vaccination rates and Twitter data collection affect the results.

- Lines 149-150: It is unclear whether RoBERTa was fine-tuned only on manually validated tweets or all hashtag-annotated ones.

- Lines 151-152: It is unclear what is evaluated, manual annotations or classification of many tweets based on RoBERTa.

- In Table 1, what exactly are the five runs? Are there five different repetitions of 200 pairs of tweets?

- Line 159: What do the authors mean by using pre-trained NER? NER will need to be combined with other geo-location services, such as those mentioned. Otherwise, I believe the services use an in-house NER system.

Figure 3: Subfigure captions are missing. They are probably the same as in the previous Figure, but they should also be mentioned here.

- Figures: The Figures are of unacceptably low quality, so they must be improved. Many of the axes are not annotated. Figures 4, 5, and 6 have the same name, and it would be clearer for the reader if they had unique names. What is CV in Figure 4?

- Figure 12: The figure seems to be missing.

- Tables: The Tables corresponding to S1 and S2 are marked as Table 11 and Table 12 later

- The authors could expand on the user-voter registration matching method and its limitations.

Reviewer #2: The manuscript offers a timely, methodologically innovative approach to studying partisan polarisation in pandemic-related discourse on Twitter (X). However, the study’s methodological transparency, and operational consistency require improvement for full clarity and robustness.

Abstract:

The Canadian context is given minimal detail in the introduction and lacks equal emphasis throughout. Especially 3rd paragraph of the abstract is primarily applied to US.

As per the authors, the finding that Canada exhibited a rare cross partisan consensus on emergency measures in offline opinion (lines 522–530), yet simultaneously showed high levels of conspiracy related content and polarisation on Twitter , raises important concerns about the representativeness of the study’s online data. This disconnect underscores that the study’s polarisation index primarily captures the discourse of politically engaged and often more extreme segments of the Twitter user base, rather than the broader Canadian public. However, this key observation from the Canadian population is missing from the abstract.

Introduction: Though the study includes 2 countries, the U.S. context is predominantly addressed; The Canadian context is given minimal detail in the introduction and lacks equal emphasis throughout. For example, in lines 58–60, the authors state that political discussions vary naturally across socio demographic groups, each having their own lexicon, and cite reference (30) in support of this. However, reference (30) focuses specifically on U.S. senators, which is a narrow and highly specific group. It is not clear how findings from that context apply to the general public, let alone to both the U.S. and Canada.

Method:

Correlation uses vaccine uptake one year after the discourse period, with no justification for the consideration of late 2020 tweets instead of mid or late 2021 tweets.

U.S. keyword list is dominated by election-specific terms and omits COVID-specific identifiers, which could bias topical coverage toward political events unrelated to public health. Whereas, the Canadian keyword list mixes political figures with explicit COVID-19 province patterns, offering better pandemic relevance. No justification is provided for this difference. Also, an explanation on how this variation may have impacted the results also missing.

Conspiracy Theory Classification: No explanation is provided on how a tweet is categorised as a conspiracy theory. Also, how was the actual conspiracy theory separated from the debunking tweet?

Sentiment: No explanation is provided on how to distinguish between endorsement, critique, or satire. Sarcasm from opposing partisans could also be misclassified as support.

The rationale for 5 tweets (Canada) and 10 tweets (U.S.) as activity thresholds is not explained.

The authors note that Canadian vaccination rates were “normalised by Canada’s 2021 population per province or territory,” but they do not clarify whether the same process was applied to the U.S. CDC vaccination data. It is quite possible that this was done or was not required for CDC data, but it should be stated explicitly for consistency.

Throughout the manuscript, there are situations where broad terms such as “comprehensive approach”, “multi‑dimensional variation”, are used without immediately describing what they mean in the current context. For instance, in the introduction, the method is described as a “comprehensive approach” to measuring polarisation, but the reader has to read further before it becomes clear whether that refers to geography, time, topic diversity, or something else. Similarly, when describing Canadian policies, phrases like “comprehensive lockdowns”, “”Specific populations” or “narrowly targeted measures” are used without explaining exactly which populations or activities were affected.

Minor: Page 11- A few inconsistencies in capitalisation (e.g., Republican party (US) or the conservative party family (Canada))

Limitations:

One point that is not currently acknowledged in the limitations section is the potential for location errors and the influence of bots. The study places users geographically based on the location information they list in their Twitter profile, processed through Open Street Map etc. While this is a reasonable method, it can still be affected if people list inaccurate, fake locations. In rare cases, VPN use might also affect the result.

Bots are another factor worth noting. Bots often provide false or generic location details and can post large volumes of highly partisan messages, which could artificially increase the apparent language gap between political groups. They can also amplify content from influential users.

**********

what does this mean?). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). 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 For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy..-->

Reviewer #1: No

Reviewer #2: No

**********

[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 . 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 . 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 . 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.. Please note that Supporting Information files do not need this step.. Please note that Supporting Information files do not need this step.. Please note that Supporting Information files do not need this step.

Dear Dr. Yang,

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 Feb 28 2026 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.. 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.. 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.. 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.

• A 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.

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 . 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 . 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 . 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,

Francesco Pierri, Ph.D.

Academic Editor

PLOS One

Journal Requirements:

1. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

2. Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

Additional Editor Comments:

The reviewers are satisfied with the revision process, however I require you address the minor comments raised by one of them in a final minor revision round.

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

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

Reviewer #1: All comments have been addressed

Reviewer #3: (No Response)

**********

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

Reviewer #1: Yes

Reviewer #3: Partly

**********

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

Reviewer #1: Yes

Reviewer #3: Yes

**********

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.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

Reviewer #3: No

**********

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

Reviewer #1: Yes

Reviewer #3: Yes

**********

Reviewer #1: The authors have addressed my remarks.The authors have addressed my remarks.The authors have addressed my remarks.The authors have addressed my remarks.

Here are two minor errors:

1. This text appears twice: "tion rates are for those who obtained at least two doses."

2. This sentence seems incomplete: "vent-triggered average polarization for identified events listed in Table 9 and Table 10 respectively."

Reviewer #3: General AssessmentGeneral AssessmentGeneral AssessmentGeneral Assessment

The manuscript addresses an interesting research question and is generally well organized. The experimental setup and analyses suggest that the authors have invested significant effort into the study. However, several conclusions are currently stronger than what is directly supported by the reported results, and important details regarding statistical analysis and data availability require clarification. The comments below reference specific sections, figures, and tables to help guide revision.

Major Comments

1. Strength of Conclusions vs. Reported Results: In the Discussion section, the authors state that the proposed approach “clearly outperforms existing methods and demonstrates robust generalizability”. However, the evidence presented in Table 3 and Figure 4 shows performance improvements that are relatively modest and, in some cases, overlapping within variance ranges. For example, the reported improvement over the baseline method in Table 3 is small on Dataset B, and no statistical significance testing is reported to confirm whether this difference is meaningful. I recommend either (i) tempering claims of “clear” or “robust” superiority, or (ii) adding appropriate statistical tests to support these statements.

2. Statistical Analysis and Reporting: The manuscript reports multiple quantitative comparisons across datasets (e.g., Section 4.2, Experimental Results), but the statistical methodology is insufficiently described.

Specific concerns include:

- The absence of statistical significance testing when comparing models in Tables 2–4.

- No reporting of confidence intervals or effect sizes, despite repeated experiments being implied.

- It is unclear whether results are based on a single run or averaged across multiple random seeds.

For instance, in Figure 5, error bars are shown, but the manuscript does not specify whether these represent standard deviation, standard error, or confidence intervals. This information is essential for interpreting result stability.

3. Data Availability and Reproducibility: While a Data Availability Statement is included, it does not appear to fully satisfy PLOS ONE’s data policy. The manuscript indicates that “processed data” were used for analysis, but the raw data underlying the results in Figures 3–6 and Tables 2–4 are not explicitly linked or deposited. In Section 3 (Methods), several preprocessing steps are described (e.g., filtering, normalization, or feature selection), but it is unclear whether the intermediate datasets produced by these steps are available.

To improve reproducibility, the authors should clarify:

- Where the raw and processed datasets can be accessed,

- Whether analysis scripts or code are publicly available,

- Or, if restrictions apply, clearly justify them.

4. Methodological Detail and Replicability: Some methodological choices lack sufficient justification or detail, particularly in Section 3.3 (Model Configuration / Experimental Setup).

Examples include:

- Hyperparameter values are listed, but the criteria for selecting them are not discussed.

- It is unclear whether validation data were used for model selection or tuning.

- The stopping criteria for training are not fully specified.

Providing this information would significantly improve the replicability of the study.

Minor Comments

1. Clarity and Precision of Language: In Section 2 (Related Work), several claims about prior methods being “limited” or “ineffective” would benefit from more precise wording or explicit citations. Some terminology is introduced informally before being defined (e.g., in Section 3.1), which may confuse readers unfamiliar with the domain.

2. Figures and Tables; Figure 2 would benefit from a more descriptive caption explaining the experimental pipeline, rather than relying on references to the main text. In Table 4, the best-performing values are highlighted, but the criteria for determining “best” (mean performance, peak value, etc.) are not explicitly stated. Axes labels and units should be double-checked for consistency across figures.

3. Minor Editorial Issues: There are a small number of grammatical and typographical errors throughout the manuscript (e.g., missing articles and inconsistent tense usage), particularly in Sections 4 and 5. These should be corrected during revision.

Summary

Overall, the manuscript presents promising work, but revisions are necessary to ensure that:

- Conclusions are proportionate to the evidence,

- Statistical analyses are transparent and rigorous,

- Data and methods are sufficiently documented to meet reproducibility standards.

**********

what does this mean?). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). If published, this will include your full peer review and any attached files.). 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 For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our For information about this choice, including consent withdrawal, please see our Privacy Policy..-->

Reviewer #1: No

Reviewer #3: Yes: Ali HatamiAli HatamiAli HatamiAli Hatami

**********

[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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Dear Dr. Yang,

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 address the comments raised by Reviewer 3 (notice that Reviewer 2 has declined a requesto re-revise the submission) for what concerns clarifications on methodological choices as well as the validity of reported results.

Please submit your revised manuscript by Apr 20 2026 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.. 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.. 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.. 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.

• A 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 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 . 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 . 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 . 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,

Francesco Pierri, Ph.D.

Academic Editor

PLOS One

Journal Requirements:

If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise.

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

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

[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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation.

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Regional and temporal patterns of partisan polarization during the COVID-19 pandemic in the United States and Canada

PONE-D-25-11475R3

Dear Dr. Yang,

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  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact  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,

Francesco Pierri, Ph.D.

Academic Editor

PLOS One

Additional Editor Comments (optional):

Reviewers' comments: