RegBR: A novel Brazilian government framework to classify and analyze industry-specific regulations

Letícia Moreira Valle; Stefano Giacomazzi Dantas; Daniel Guerreiro e Silva; Ugo Silva Dias; Leonardo Monteiro Monasterio

doi:10.1371/journal.pone.0275282

Peer Review History

Original SubmissionFebruary 10, 2022
10 Aug 2022 Decision Letter - Sathishkumar V E, Editor PONE-D-22-04202RegBR: A novel Brazilian government framework to classify and analyze industry-specific regulationsPLOS ONE Dear Dr. Valle, 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 Sep 24 2022 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, Sathishkumar V E 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 Thank you for stating in your Funding Statement: “This research was partially supported by the National School of Public Administration – ENAP, Government of Brazil (Grant TED UnB-ENAP 83/2018).” Please provide an amended statement that declares all the funding or sources of support (whether external or internal to your organization) received during this study, as detailed online in our guide for authors at http://journals.plos.org/plosone/s/submit-now. Please also include the statement “There was no additional external funding received for this study.” in your updated Funding Statement. Please include your amended Funding Statement within your cover letter. We will change the online submission form on your behalf. 3. Thank you for stating the following in the Acknowledgments Section of your manuscript: “The authors wish to thank the National School of Public Administration (ENAP) for all the support and partnership within the development of the RegBR project, providing funding, infrastructure and establishing contact with regulatory agencies. We also would like to thank the relevant feedback received by the Brazilian regulatory agencies, who contributed with clear ideas so that the project could be used in practice by police makers” We note that you have provided additional information within the Acknowledgements Section that is not currently declared in your Funding Statement. Please note that funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form. Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows: “This research was partially supported by the National School of Public Administration – ENAP, Government of Brazil (Grant TED UnB-ENAP 83/2018).” Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 4. 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.] 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 #3: No Reviewer #4: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #3: Yes Reviewer #4: 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 #3: Yes Reviewer #4: 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 #3: Yes Reviewer #4: 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 #3: RegBR: A novel Brazilian government framework to classify and analyze industry specific Regulations Reviewer Comments: In this paper, the authors apply machine learning, deep learning and transfer learning models along with word weighting and embedding schemes to generate framework to classify industry specific regulations. The various combinations of techniques used by the authors are appreciable. The paper is well organized and written. The interpretation and description of the experimental results are also explained clearly. However, this manuscript have some weak points, it should be further improved before consider for publication. Some of my observations are 1. Figures 1,2,3,7 need to be drawn clearly and explanation about each figure to be incorporated in corresponding section. 2. In figure 5, x-axis legend is not mentioned and proper explanation is required. 3. In figure 9, only 8 classes are displayed? What about other classes. Justification is required. 4. Why validation is not performed? Justify 5. Why the authors specifically choose CNN and LSTM classifiers? 6. According to the results obtained, if statistical models perform better than machine, deep and transfer learning models, then what is the use of these latest techniques for analysis? Is hypertuning of these models not done properly? Justification is required. Reviewer #4: Manuscript needs English language check as the sentence formation errors occur throughout the manuscript What strategy is used to select hyperparameters? Explain the dataset used in detail. Make a table to summarize the dataset features. Explain the proposed work in detail Elaborate Normative acts. Application of the proposed system should be explained in detail. What is the need of using ensemble classifier? Whole manuscript should be reorganised following standard scientific article requirements ****** 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 #3: No Reviewer #4: Yes: Usha Moorthy ******** [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. Attachments Attachment Submitted filename: Plos one-review comments-07.08.22.docx https://doi.org/10.1371/journal.pone.0275282.r001
Revision 1
2 Sep 2022 Author Response Dear Prof. Sathishkumar V E, On behalf of all the authors of the manuscript "RegBR: A novel Brazilian government framework to classify and analyze industry-specific regulations," we would like to thank you very much for revising our manuscript and for the relevant comments provided by you and the two reviewers, which helped us to improve our work. We submit our revised manuscript for appreciation and also a point-by-point response to the reviewer's comments. As suggested in the decision e-mail, we also decided to modify the funding statement in order to suit the journal's requirements. The new funding statement is as follows: This research was supported by the National School of Public Administration – ENAP, Government of Brazil (Grant TED UnB-ENAP 83/2018). There was no additional external funding received for this study. For the acknowledgements section of our manuscript, we also like to slightly modify the statement to the following one: The authors wish to thank the National School of Public Administration (ENAP) for all the support and partnership in the development of the RegBR project. We also would like to thank the relevant feedback received by the regulatory agencies, which contributed with clear ideas so that the project could be used in practice by policy makers. We hope that the improvements we have made to this paper will be enough to enable it to be considered for publication by this renowned journal. Thank you for considering our manuscript. Best regards, The authors __________________________ Academic editor: 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_affiliation s.pdf R. We have made changes to figures, tables, and author affiliations formatting and we now confirm that our manuscript meets PLOS ONE’s style requirements. We used PACE digital diagnostic tool to ensure that our Figures meet PLOS requirements. 2 Thank you for stating in your Funding Statement: “This research was partially supported by the National School of Public Administration – ENAP, Government of Brazil (Grant TED UnB-ENAP 83/2018).” Please provide an amended statement that declares all the funding or sources of support (whether external or internal to your organization) received during this study, as detailed online in our guide for authors at http://journals.plos.org/plosone/s/submit-now. Please also include the statement “There was no additional external funding received for this study.” in your updated Funding Statement. Please include your amended Funding Statement within your cover letter. We will change the online submission form on your behalf. R. We would like to change our funding statement to the following: “This research was supported by the National School of Public Administration – ENAP, Government of Brazil (Grant TED UnB-ENAP 83/2018). There was no additional external funding received for this study.” 3. Thank you for stating the following in the Acknowledgments Section of your manuscript: “The authors wish to thank the National School of Public Administration (ENAP) for all the support and partnership within the development of the RegBR project, providing funding, infrastructure and establishing contact with regulatory agencies. We also would like to thank the relevant feedback received by the Brazilian regulatory agencies, who contributed with clear ideas so that the project could be used in practice by police makers” We note that you have provided additional information within the Acknowledgements Section that is not currently declared in your Funding Statement. Please note that funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form. Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows: “This research was partially supported by the National School of Public Administration – ENAP, Government of Brazil (Grant TED UnB-ENAP 83/2018).” Please include your amended statements within your cover letter; we will change the online submission form on your behalf. R. We also would like to change our Acknowledgments section to the following: The authors wish to thank the National School of Public Administration (ENAP) for all the support and partnership in the development of the RegBR project. We also would like to thank the relevant feedback received by the regulatory agencies, which contributed with clear ideas so that the project could be used in practice by policy makers. 4. 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. R. We have confirmed that our reference list is complete and correct. __________________________________ Reviewers' comments: ● Reviewer #3 In this paper, the authors apply machine learning, deep learning and transfer learning models along with word weighting and embedding schemes to generate framework to classify industry specific regulations. The various combinations of techniques used by the authors are appreciable. The paper is well organized and written. The interpretation and description of the experimental results are also explained clearly. However, this manuscript have some weak points, it should be further improved before consider for publication. Some of my observations are R. The modifications associated with reviewers' #3 comments are highlighted in green in the Revised Manuscript with Track Changes document. Next, we provide a point-by-point response to the reviewers' #3 comments. 1. Figures 1,2,3,7 need to be drawn clearly and explanation about each figure to be incorporated in corresponding section. R. Thank you for this comment. We have redrawn the indicated Figures and added a clearer explanation in the corresponding sections. In order to adapt our work to the journal's style format, some tables have become figures and that's why the new figures in this comment are now the Figures 2, 3, 4 and 8. 2. In figure 5, x-axis legend is not mentioned and proper explanation is required. R. Thank you for noticing that. We adjusted the image adding the x-axis legend and its scale. Also, we added a paragraph explaining the image and an example of its interpretation. Fig 5 is now named as Fig 6. 3. In figure 9, only 8 classes are displayed? What about other classes. Justification is required. R. We appreciate the question. In response, we only displayed the classes that presented a significant correlation level between their KPCA projection and their complexity metrics. A total of 8 classes satisfied these conditions. We made it clearer in the manuscript, at the subsection Linguistic complexity right before Fig 9. 4. Why validation is not performed? Justify R. Thank you for bringing up this point. In fact, RegBR is the first Brazilian regulatory framework that creates centralized regulatory metrics, and for this reason, there is no similar work to be compared with. On the other hand, we can correlate the observed results with known episodes of regulatory change in Brazilian history, such as the time of the creation of the regulatory agencies, the implementation of new economic plans or the energy crisis that happened in the 2000s, as related in the Regulatory metrics conception subsection. Also, after presenting the results to the national regulatory agencies, we received feedback in the sense that our metrics results corroborated with internal metrics created by the agencies. An example of this fact is that the national water agency (ANA), which uses a plain language approach to monitor the linguistic complexity of their texts, informs us that they were expecting ANA’s agency to have one of the biggest linguistic complexity within the sectors for the types of normative acts analyzed in our work, which was confirmed by our linguistic complexity metric. 5. Why the authors specifically choose CNN and LSTM classifiers? R. Thank you for the question. The reasons for choosing CNN and LSTM are based on two main factors. First, they are often used in many NLP applications. Secondly, before the creation of the Transformer architecture, they were used as building blocks for some state-of-the-art NLP models. These two points led us to include models based on these two neural network designs to our benchmark. We added a paragraph in the manuscript to make that choice clearer. 6. According to the results obtained, if statistical models perform better than machine, deep and transfer learning models, then what is the use of these latest techniques for analysis? Is hypertuning of these models not done properly? Justification is required. R. Thank you for raising this point. We added more information in the text regarding the importance of benchmarking different models. For some NLP tasks, such as translation, there are standard datasets that are used to evaluate models. In that case, comparing the proposed model with the current state-of-the-art is enough most of the time. However, in our application, there were no past performances to serve as a baseline to indicate what would be considered a "good" model. Thus, we performed an evaluation of different models and approaches. With regard to the hypertuning, we used grid-search with the values for the parameters that are described in the literature and we have updated this information in the manuscript. Moreover, in the text, we raised some possible reasons why the transfer-learning methods presented underwhelming results. Once again, we thank the reviewer for devoting his/her time to assess our manuscript and for the helpful comments which have guided us to enrich the original manuscript. We hope that our manuscript and revision of the manuscript are satisfactory. ● Reviewer #4 R. The modifications associated with reviewers' 4 comments are highlighted in orange in the Revised Manuscript with Track Changes document. Next, we provide a point-by-point response to the reviewers' 4 comments. 1. Manuscript needs English language check as the sentence formation errors occur throughout the manuscript R. We performed a manuscript language review and corrected grammar and sentence formation errors. We hope that this revised version of the manuscript will meet the language requirements. 2. What strategy is used to select hyperparameters? R. Thank you for your question. We made it clearer in the paper how we select the hyperparameters. We performed a grid-search using the hyperparameter values often used in the literature for this kind of task. 3. Explain the dataset used in detail. Make a table to summarize the dataset features. R. Thank you for the comments. In the text classification task, all the features were derived from the normative act texts themselves. To summarize the data workflow, first we build an ETL (Extract, transform, load) system to gather normative act texts from various sources and centralize them in a database. Then, we prepared the data by removing stop words, malformed characters and numbers, and standard sentences and headers that appear in all normative texts. Lastly, we transform text to numeral representation in different ways depending on the model used, like using tf-idf, word embeddings, or in the case of transformer-based models, the specific encoder proposed by the model architecture. More details on each model's feature extraction approach are available in the subsection Details on Text Classification. 4. Explain the proposed work in detail R. Our paper proposes a novel regulatory framework applicable to Brazil with the goal of producing relevant information on the national regulatory situation in order to: promote active transparency of public information; subsidize new regulatory studies based on RegBR data; and assist decision makers to measure what their organization produces in terms of volume and characteristics of regulations. For the first time, we classify normative acts in industry-specific classes and create a set of new regulatory metrics that concern linguistic complexity, restrictiveness, legal interest, and industry-specific citation relevance. We made some adjustments in the manuscript such that the goals and applications of the proposed work are better explained. 5. Elaborate Normative acts. R. By a dictionary definition, a normative act means any law, decree, resolution, regulation, administrative direction, instruction, rule, ordinance, or other decision that creates legal consequences for more than one individual. We also added this definition in the manuscript, in the Normative Acts data structure subsection. 6. Application of the proposed system should be explained in detail. R. Thank you for raising this point. We are producing a second paper focused exclusively on RegBR applications, but in order to make the applications clear in this article, we added a new paragraph in the Introduction section explaining in more detail the possible applications of the system. 7. What is the need of using ensemble classifier? R. Ensemble models tend to yield better results when there is a significant diversity among the models. In our case, we combine a ridge classifier, which is a classifier that converts the task into a regression and generates labels accordingly, and an SVM classifier. These two models have a few complementary strengths and weaknesses, and when combined, generate a more precise and robust prediction. 8. Whole manuscript should be reorganised following standard scientific article requirements R. Parts of the manuscript text, figures, and tables have been rewritten so we could meet all PLOS ONE organization and style requirements available in https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_b ody.pdf. We hope that the improvements we have made to this paper should be enough to enable it to be published by this renowned journal. We remain open to modifying specific parts of the manuscript that you feel don't meet the journal requirements. We would like to thank the reviewer for providing some helpful comments and suggestions that have improved our manuscript. We hope that our responses and revisions of the manuscript are satisfactory. Attachments Attachment Submitted filename: Response to Reviewers .pdf https://doi.org/10.1371/journal.pone.0275282.r002
13 Sep 2022 Decision Letter - Sathishkumar V E, Editor RegBR: A novel Brazilian government framework to classify and analyze industry specific regulations. PONE-D-22-04202R1 Dear Dr. Valle, 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 for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org. 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, Sathishkumar V E Academic Editor PLOS ONE Additional Editor Comments (optional): 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 #2: All comments have been addressed Reviewer #4: (No Response) ******** 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 #2: Yes Reviewer #4: (No Response) ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #2: Yes Reviewer #4: (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 #2: Yes Reviewer #4: (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 #2: Yes Reviewer #4: (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 #2: Accepted, the author has incorporated all the comments. In its current form the paper ua ready for publication Reviewer #4: (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 #2: No Reviewer #4: Yes: Usha Moorthy ******** https://doi.org/10.1371/journal.pone.0275282.r003
Formally Accepted
19 Sep 2022 Acceptance Letter - Sathishkumar V E, Editor PONE-D-22-04202R1 RegBR: A novel Brazilian government framework to classify and analyze industry-specific regulations Dear Dr. Moreira Valle: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. 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. If we can help with anything else, please email us at plosone@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Sathishkumar V E Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0275282.r004

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .