Social Networks in Military Powers: Network and Sentiment Analysis during the COVID-19 Pandemic

Round 1

Reviewer 1 Report

This study aimed to search for indicators of differential behavior in the official profiles of the main military forces on social networks during the Covid-19 pandemic. The techniques of social network analysis, as well as sentiment analysis were used to investigate the content of the posts. Significant differences were observed between the behavior on social media and the organizational and communicative culture of the nations.

The topic is very interesting. The methodology is adequately described. Figures and tables are useful. The results are clear and adequately discussed.

I would like to make the following minor suggestions:

-In the abstract, maybe it would be better to omit the words/descriptions background, and conclusions because the content is clear.

-The introduction section seems to be more extensive than the reader may anticipate. Maybe, It would be better to maintain the most relevant information and add a theoretical background section after the introduction. I have the same impression about the discussion section too.

 

- There are grammatical, punctuation, and/or spelling errors, but overall, they do not detract too much from reading the paper. It would be useful to make a final check. Check titles and subtitles.

 

There are grammatical, punctuation, and/or spelling errors, but overall, they do not detract too much from reading the paper. It would be useful to make a final check. Check titles and subtitles.

Author Response

Computation-2425112

Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic

RESPONSE TO THE DECISION LETTER

 

Dear Editor of the Journal of Computation.

We would like to thank you for considering our work entitled “Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic” as conditionally accepted for publication in the Journal of Computation. We want to show our gratitude to you for your support in the review process.

We would also like to thank your team of Reviewers for their valuable comments on and constructive ideas for our manuscript during the review process. We really appreciate your comments. We believe the amendments made have significantly improved the article.

We would especially like to thank the kind words of most of the reviewers about the methodological quality of our research. We are very grateful for their words as we strive to improve every research we conduct.

We have carried out the following steps in order to respond to these comments and so improve the article.

 

 

 

REVIEWER 1

General comment:

This study aimed to search for indicators of differential behavior in the official profiles of the main military forces on social networks during the Covid-19 pandemic. The techniques of social network analysis, as well as sentiment analysis were used to investigate the content of the posts. Significant differences were observed between the behavior on social media and the organizational and communicative culture of the nations.

The topic is very interesting. The methodology is adequately described. Figures and tables are useful. The results are clear and adequately discussed.

 

General response:

Dear Reviewer. Thank you very much for your kind words. We have taken into account all your comments to improve the paper. We thank you very much for your time and effort in helping us to improve our work. We hope to meet your expectations.

I would like to make the following minor suggestions:

Comment 1:

-In the abstract, maybe it would be better to omit the words/descriptions background, and conclusions because the content is clear.

Response 1:

Dear Reviewer. Thank you very much, we have made the changes. In addition, we have made other changes requested by your colleague. We hope we have improved the quality.

Please revise the following lines:

 The outbreak of the Covid-19 pandemic shifted socialization and information seeking to social media platforms. The Armed Forces of the major military powers initiated civil support operations to combat the invisible and common enemy. The aim of this study is to analyze the existence of differential behavior in the corporate profiles of the major military powers on Twitter, Instagram, and Facebook during the Covid-19 pandemic. The principles of social network analysis were followed, along with sentiment analysis, to study web positioning and the emotional content of the posts (N=25,328).The principles of data mining were applied to process the KPIs (Fanpage Karma software), and artificial intelligence (meaning cloud algorithym) sentiment analysis was applied to study the emotionality of the publications. The analysis was carried out using the IBM SPSS Statistics 25 statistical software. Subsequently, a qualitative content analysis was carried out using frequency graphs or word clouds ("nubedepalabras" app in English word cloud).Significant differences are found between the behavior on social media and the organizational and communicative culture of the nations. It is highlighted that some nations present different preferences than the main communicative strategy developed by their Armed Forces. The corporate communication of the major military powers should consider the emotional nature of their posts to align with the preferences of their population.

 

Comment 2:

The introduction section seems to be more extensive than the reader may anticipate. Maybe, It would be better to maintain the most relevant information and add a theoretical background section after the introduction. I have the same impression about the discussion section too.

Response 2:

Dear Reviewer. Thank you for your honesty. We think it is a good idea to include two sections to facilitate  understanding. We have made the change.

We have replaced the section about historical contextualization as an introduction. In this way, we introduce the reader to the specific social moment and in the theoretical review section we explain the study variables in more detail. Regarding the discussion, we have also included various sections. Additionally, we have added a conclusion.

Comments on the Quality of English Language:

Comment 3:

There are grammatical, punctuation, and/or spelling errors, but overall, they do not detract too much from reading the paper. It would be useful to make a final check. Check titles and subtitles.

Response 3:

Dear reviewer. Thank you very much. We have done a final check and we fixed the changes (in yellow)

 

Author Response File: Author Response.docx

Reviewer 2 Report

After careful reading the paper, I have some suggestions.

1. Abstract: Keywords are not matching: I suggest it should be:

Covid-19, social media platforms, Armed Forces, communicative strategy, corporate communication

2. According to my personal opinion, the paper uses statistical methods to do the cardinal analysis, but the calculation process did not be sufficient. Especially, in Figure 1, it is recommended to analyze the figure and content separately. In addition, the description of Figure 2 did not appear; which cannot make it easy for readers to understand. Please recheck.

3. According to the witting style of full manuscript, the paper should include conclusion, but it did not appear. Please recheck.

4. The Reference: REF[16], REF[18], REF[28], REF[33] and REF[34] are too far away. Please use newest reference to replace.

Author Response

Computation-2425112

Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic

RESPONSE TO THE DECISION LETTER

 

Dear Editor of the Journal of Computation.

We would like to thank you for considering our work entitled “Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic” as conditionally accepted for publication in the Journal of Computation. We want to show our gratitude to you for your support in the review process.

We would also like to thank your team of Reviewers for their valuable comments on and constructive ideas for our manuscript during the review process. We really appreciate your comments. We believe the amendments made have significantly improved the article.

We would especially like to thank the kind words of most of the reviewers about the methodological quality of our research. We are very grateful for their words as we strive to improve every research we conduct.

We have carried out the following steps in order to respond to these comments and so improve the article.

 

 

REVIEWER 2

After careful reading the paper, I have some suggestions.

Comment 1:

1. Abstract: Keywords are not matching: I suggest it should be:

Covid-19, social media platforms, Armed Forces, communicative strategy, corporate communication

Response 1:

Dear Reviewer. Thank you very much, we thought it was a very good idea. We have made the change.

Please revise the following lines:

Keywords:  Covid-19, social media platforms, Armed Forces, communicative strategy, corporate communication

 

Comment 2:

2. According to my personal opinion, the paper uses statistical methods to do the cardinal analysis, but the calculation process did not be sufficient. Especially, in Figure 1, it is recommended to analyze the figure and content separately. In addition, the description of Figure 2 did not appear; which cannot make it easy for readers to understand. Please recheck.

Response 2:

Dear reviewer, thank you very much for your comment. To enhance the understanding of the methodology and results, we have added a new section titled "Data Analysis" where the conducted analyses are explained.

Please review the following lines:

3.4. Data analysis

    A series of analyses are necessary to either accept or refute the hypotheses. The software used was IBM SPSS.

Firstly, the descriptive results of each KPI and sentiment analysis in terms of means - a measure of central tendency that represents the average value of a set of data - and standard deviation - indicates the data dispersion around the mean - should be analyzed for each nation and social network.

In order to compare both KPIs and sentiment analysis variables between nations for each social network, an Analysis of Variance (ANOVA) test was applied for scale variables (polarity) and ratio variables (KPIs). ANOVA is a statistical test used to compare the means of three or more groups and determine if there are significant differences between them. It allows evaluating whether the observed differences in the data are a result of variability between groups or simply due to chance. ANOVA is based on analyzing the variance of the data to make statistical inferences.

For dichotomous variables (subjectivity, irony, and emotional agreement), a Chi-square test (χ²) was applied, which is used to determine if there is a significant relationship between two categorical variables.

To visualize these results more effectively, heatmaps were created using Excel software. A heatmap is a visual representation that uses colors to display the distribution or variation of a variable in a data matrix or table. It is commonly used to highlight patterns, trends, or concentrations of values in a dataset. The intensity of the color in each cell of the heatmap provides a quick visualization of the magnitude or density of the values. Cells with higher values will be displayed with more intense or darker colors, while cells with lower values will be displayed with lighter colors.

To test the strength of sentiment analysis in posts regarding the number of likes, multiple regression analysis was applied, which is a statistical technique that seeks to establish a relationship between a dependent variable and two or more independent variables. It is used to predict or explain the value of a dependent variable based on independent variables.

To visualize these results more effectively, word clouds were created [45]. Word clouds are generated by algorithms that process the text and determine the frequency of each word. Based on this information, visualizations are created where the most common words are presented in a larger size and placed in random or structured positions in the image. This technique is widely used to summarize or visualize patterns in large amounts of text [59]. For example, it can be applied in user opinion analysis, surveys, blogs, articles, political speeches, among others. By looking at a word cloud, it is possible to get a general idea of the most important or recurring topics within a set of texts without having to read all the content. Word clouds are useful for highlighting trends, identifying keywords, quickly understanding the content of a text, or simply making a set of words visually appealing [60]. There are various online tools and specialized software that allow for generating customized word clouds, adjusting parameters such as shape, color, fonts, and size of the cloud. In our case, we used the "nubesdepalabras" application, following the methodological principles of Krippendorff. Duplicates and meaningless words such as prepositions and articles were eliminated. Thus, the unit of analysis is meaningful words, with the most frequent ones represented in a larger size. They are organized into two typologies of categories: a) thematic (a.1 national identity, a.2 military jargon or terminology, a.3 current news), and b) type of language (b.1 technical-military, where everyday activities such as maneuvers, training, or materials are presented, and b.2 humanitarian, with information about values, civil support actions, or protection of vulnerability).

We appreciate you bringing to our attention the absence of the description of Figure 2 in the text. We have included it within the text. Thank you again.

 

 

Comment 3:

3. According to the witting style of full manuscript, the paper should include conclusion, but it did not appear. Please recheck.

Response 3:

Dear reviewer, we have added a comprehensive conclusion section. Thank you for your suggestion.

Comment 4:

4. The Reference: REF[16], REF[18], REF[28], REF[33] and REF[34] are too far away. Please use newest reference to replace.

Response 4:

Dear reviewer, thank you for your recommendation. We have updated the following references: REF[16], REF[18], and REF[33].

Regarding REF[28], we have included a more recent reference from other authors on the same topic of organizational culture.

Regarding REF[34], we have included the most recent publication by the same author, considered a classic in Social Psychology and a primary source on intergroup relations.

 

Author Response File: Author Response.docx

Reviewer 3 Report

Dear Authors,

The paper is well-written and interesting. I just have some comments:

- Abstract can be better with add more details related to methodology.

- The methodology part needs to revise. Please write more about your method. Which software did you use? Why didn't use Python? 

- Conclusion part can be more clear if adding at least one more paragraph just related to what was the implication of the results. Does it mean that what is the main tangible result you obtained from this research? How this result can be influenced regarding to topic?

Author Response

Computation-2425112

Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic

RESPONSE TO THE DECISION LETTER

 

Dear Editor of the Journal of Computation.

We would like to thank you for considering our work entitled “Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic” as conditionally accepted for publication in the Journal of Computation. We want to show our gratitude to you for your support in the review process.

We would also like to thank your team of Reviewers for their valuable comments on and constructive ideas for our manuscript during the review process. We really appreciate your comments. We believe the amendments made have significantly improved the article.

We would especially like to thank the kind words of most of the reviewers about the methodological quality of our research. We are very grateful for their words as we strive to improve every research we conduct.

We have carried out the following steps in order to respond to these comments and so improve the article.

REVIEWER 3

Dear Authors,

The paper is well-written and interesting. I just have some comments:

 

Comment 1:

Abstract can be better with add more details related to methodology.

Response 1:

Dear Reviewer. Thank you very much, we have made the changes.

Please revise the following lines:

Abstract: The outbreak of the Covid-19 pandemic shifted socialization and information seeking to social media platforms. The Armed Forces of the major military powers initiated civil support operations to combat the invisible and common enemy. The aim of this study is to analyze the existence of differential behavior in the corporate profiles of the major military powers on Twitter, Instagram, and Facebook during the Covid-19 pandemic. The principles of social network analysis were followed, along with sentiment analysis, to study web positioning and the emotional content of the posts (N=25,328).The principles of data mining were applied to process the KPIs (Fanpage Karma), and artificial intelligence (meaning cloud) sentiment analysis was applied to study the emotionality of the publications. The analysis was carried out using the IBM SPSS Statistics 25 statistical software. Subsequently, a qualitative content analysis was carried out using frequency graphs or word clouds ("nubedepalabras" in English word cloud).Significant differences are found between the behavior on social media and the organizational and communicative culture of the nations. It is highlighted that some nations present different preferences than the main communicative strategy developed by their Armed Forces. The corporate communication of the major military powers should consider the emotional nature of their posts to align with the preferences of their population.

Comment 2:

The methodology part needs to revise. Please write more about your method. Which software did you use? Why didn't use Python? 

Response 2:

Dear reviewer, thank you very much for your comment. To clarify the data analysis, we have added a new section to the methodology called "Data Analysis". In this way, we aim to improve the understanding of all the analyses we have conducted. Additionally, we have provided details about the software we have used (highlighted in intense yellow). Please review the following lines:

3.4. Data analysis

    A series of analyses are necessary to either accept or refute the hypotheses. The software used was IBM SPSS.

Firstly, the descriptive results of each KPI and sentiment analysis in terms of means - a measure of central tendency that represents the average value of a set of data - and standard deviation - indicates the data dispersion around the mean - should be analyzed for each nation and social network.

In order to compare both KPIs and sentiment analysis variables between nations for each social network, an Analysis of Variance (ANOVA) test was applied for scale variables (polarity) and ratio variables (KPIs). ANOVA is a statistical test used to compare the means of three or more groups and determine if there are significant differences between them. It allows evaluating whether the observed differences in the data are a result of variability between groups or simply due to chance. ANOVA is based on analyzing the variance of the data to make statistical inferences.

For dichotomous variables (subjectivity, irony, and emotional agreement), a Chi-square test (χ²) was applied, which is used to determine if there is a significant relationship between two categorical variables.

To visualize these results more effectively, heatmaps were created using Excel software. A heatmap is a visual representation that uses colors to display the distribution or variation of a variable in a data matrix or table. It is commonly used to highlight patterns, trends, or concentrations of values in a dataset. The intensity of the color in each cell of the heatmap provides a quick visualization of the magnitude or density of the values. Cells with higher values will be displayed with more intense or darker colors, while cells with lower values will be displayed with lighter colors.

To test the strength of sentiment analysis in posts regarding the number of likes, multiple regression analysis was applied, which is a statistical technique that seeks to establish a relationship between a dependent variable and two or more independent variables. It is used to predict or explain the value of a dependent variable based on independent variables.

To visualize these results more effectively, word clouds were created [45]. Word clouds are generated by algorithms that process the text and determine the frequency of each word. Based on this information, visualizations are created where the most common words are presented in a larger size and placed in random or structured positions in the image. This technique is widely used to summarize or visualize patterns in large amounts of text [59]. For example, it can be applied in user opinion analysis, surveys, blogs, articles, political speeches, among others. By looking at a word cloud, it is possible to get a general idea of the most important or recurring topics within a set of texts without having to read all the content. Word clouds are useful for highlighting trends, identifying keywords, quickly understanding the content of a text, or simply making a set of words visually appealing [60]. There are various online tools and specialized software that allow for generating customized word clouds, adjusting parameters such as shape, color, fonts, and size of the cloud. In our case, we used the "nubesdepalabras" application, following the methodological principles of Krippendorff. Duplicates and meaningless words such as prepositions and articles were eliminated. Thus, the unit of analysis is meaningful words, with the most frequent ones represented in a larger size. They are organized into two typologies of categories: a) thematic (a.1 national identity, a.2 military jargon or terminology, a.3 current news), and b) type of language (b.1 technical-military, where everyday activities such as maneuvers, training, or materials are presented, and b.2 humanitarian, with information about values, civil support actions, or protection of vulnerability).

 

We were not familiar with the software Python. As a psychology group, we greatly appreciate your input. We have discussed the possibility of acquiring and training in Python in our Department. It seems like a very interesting opportunity for us to learn in the future. Once again, we appreciate your honesty and transparency.

Comment 3:

Conclusion part can be more clear if adding at least one more paragraph just related to what was the implication of the results. Does it mean that what is the main tangible result you obtained from this research? How this result can be influenced regarding to topic?

Response 3:

Dear reviewer, thank you very much for your comment. Following your suggestion, we have included two sections: the section on practical applications, where we have incorporated a final reflection (highlighted in intense yellow) and the section on limitations and future prospects.We hope to meet your expectations.

Please review the following lines:

5.3. Practical Applications

As practical applications of this research, it is highlighted the importance for military profiles to collaborate in the construction of the virtual community by paying attention to the language, emotional tone, and topics that their population reinforces through the use of likes. Thus, the principles developed by Hallahan [15] are proposed: a) engaging with the community by generating dialogues, b) promoting philanthropy, and c) showcasing social responsibility actions. Similarly, posts with positive sentiments that demonstrate positive leadership are more accepted by the population, as long as the nation is not involved in an armed conflict. However, the change in corporate communication management must start with dialogue, establishing trust and breaking cultural barriers in order to find common ground  [32]. The importance of building a sense of digital community in the Armed Forces is emphasized. This entails the strategic management of corporate communication, aligning the mission with the vision to connect synchronously with the thoughts and sentiments of society.

 

5.4. Limitations, and Prospective Studies

Regarding limitations, it is important to note that the analysis dates correspond to the early stage of the Covid-19 pandemic, representing a specific and highly connected moment. Secondly, it is necessary to determine the existence of differences between temporal phases, as some studies suggest that during the first months of the pandemic, when social distancing measures were very strict, connectivity increased. Thirdly, the social media platform YouTube was omitted because during the data collection process, issues were identified that could jeopardize the reliability of the data. The received "likes" may be altered due to the presence of fake profiles that aim to troll cooperative profiles, so the research would benefit from using software like Graphex to study the community in detail and exclude profiles that generate only noise. In this sense, as the study relies on data from social media, there may be inherent biases or inaccuracies in this data, which should be acknowledged. Also, while the study focuses on major military powers, it is unclear whether these findings would extend to smaller nations or non-military organizations. Furthermore, it is necessary to take into account methodological considerations, as indicated by Wei Wei et al. [63]. When dealing with information from a post published on social networks, it is important to approach it from natural language processing (NLP) as a task of natural language understanding (NLU). In this regard, many methods overlook the importance of natural language comprehension. Hence, the need to employ classification methods called LSTM-SN (Long Short-Term Memory Recurrent Neural Network Fusion Social Network) is proposed [63].

Furthermore, we have added a dedicated conclusion section to provide a clearer overview of the main results.

Please review the following lines:

6. Conclusion

In summary, it is concluded that the profiles of the Armed Forces of major military powers do not fully align with the preferences of their virtual community. Military powers offer a highly technical and objective view of their reality, showcasing their professionalism and technical capabilities in line with military values. Despite significant differences observed among nations, in general, the virtual community demands positive, subjective, and emotionally diverse posts. In other words, human behavior on social networks requires adherence to a set of social norms that include slang and language from pop culture, as well as a relative "dramatization" of events, while also emphasizing pro-social and altruistic actions.

 

Reviewer 4 Report

The paper's focus on the unique intersection of military powers, social media communication, and sentiment analysis in the context of the Covid-19 pandemic provides an insightful perspective. Here are some comments that might be beneficial for the revision:

Strengths:

·        Novelty and Relevance: The investigation of how military powers use social media in times of crisis is both novel and timely. The Covid-19 pandemic setting adds further relevance to your study.

·        Robust Methodology: The utilization of social network analysis and sentiment analysis to examine web positioning and emotional content is methodologically sound. The large number of posts (N=25,328) examined also lends robustness to your study.

·        Clear Hypotheses: The hypotheses of the study are clear and well-structured, providing a solid framework for your research.

Weaknesses:

Clarification of Key Concepts: Some key terms and concepts (such as key performance indicators) need a more detailed explanation to ensure accessibility to a broader audience.

Lack of Comparative Analysis: The study mentions significant differences between nations but doesn't sufficiently discuss what these differences are or provide a comparative analysis. The authors need to discuss in-depth the national differences in various kinds of networks such as research publication networks (doi:10.1108/JD-02-2022-0030), social network (doi:10.1007/s11227-022-05034-w) or Instagram comments on COVID-19 (doi:10.5755/j01.itc.51.3.30276).

Unclear Implications: While the conclusion highlights the need for corporate communication to align with the emotional nature of posts, it would be beneficial to expand on the implications of your findings.

Limitations:

·        Generalizability: While the study focuses on major military powers, it is unclear whether these findings would extend to smaller nations or non-military organizations.

·        Bias in Social Media Data: As the study relies on data from social media, there may be inherent biases or inaccuracies in this data, which should be acknowledged. 

·        The lack of meaningful conclusions: I did not find any conclusions, just a discussion.

Minor issues:

·        There are instances of non-English text in multiple places across the manuscript.

Conclusion: Your study represents an interesting contribution to the research on social media usage and sentiment analysis during crises, particularly within the context of military institutions. By addressing these points in a Major revision, you could further strengthen your manuscript.

Author Response

Computation-2425112

Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic

RESPONSE TO THE DECISION LETTER

 

Dear Editor of the Journal of Computation.

We would like to thank you for considering our work entitled “Social networks in military powers: network and sentiment analysis during the Covid-19 pandemic” as conditionally accepted for publication in the Journal of Computation. We want to show our gratitude to you for your support in the review process.

We would also like to thank your team of Reviewers for their valuable comments on and constructive ideas for our manuscript during the review process. We really appreciate your comments. We believe the amendments made have significantly improved the article.

We would especially like to thank the kind words of most of the reviewers about the methodological quality of our research. We are very grateful for their words as we strive to improve every research we conduct.

We have carried out the following steps in order to respond to these comments and so improve the article.

REVIEWER 4

The paper's focus on the unique intersection of military powers, social media communication, and sentiment analysis in the context of the Covid-19 pandemic provides an insightful perspective. Here are some comments that might be beneficial for the revision:

Strengths:

Comment 1:

Novelty and Relevance: The investigation of how military powers use social media in times of crisis is both novel and timely. The Covid-19 pandemic setting adds further relevance to your study.

Robust Methodology: The utilization of social network analysis and sentiment analysis to examine web positioning and emotional content is methodologically sound. The large number of posts (N=25,328) examined also lends robustness to your study.

Clear Hypotheses: The hypotheses of the study are clear and well-structured, providing a solid framework for your research.

Response 1:

Dear reviewer, thank you very much for your positive evaluation of our work. We have taken into account all of your comments to improve the article.

Weaknesses:

Comment 2:

Clarification of Key Concepts: Some key terms and concepts (such as key performance indicators) need a more detailed explanation to ensure accessibility to a broader audience.

Response 2:

Dear reviewer, thank you very much for your comment. We have clarified key concepts such as KPI, word cloud, and heatmaps. We have also clarified statistical and methodological terms such as ANOVA and Chi-square test. We hope to have improved the quality of the research.

 

Comment 3:

Lack of Comparative Analysis: The study mentions significant differences between nations but doesn't sufficiently discuss what these differences are or provide a comparative analysis. The authors need to discuss in-depth the national differences in various kinds of networks such as research publication networks (doi:10.1108/JD-02-2022-0030), social network (doi:10.1007/s11227-022-05034-w) or Instagram comments on COVID-19 (doi:10.5755/j01.itc.51.3.30276).

Response 3:

Dear reviewer, thank you very much for your comment. We found the references you provided to be very interesting.

We have used the first reference to initiate section 5.2, which discusses cultural differences among nations during the Covid period.

Please review the following lines:

5.2. Differences between nations

 

Previous studies on social networks and the activity of researchers during the Covid-19 period have found significant differences between nations, taking into account Hofstede's cultural model [62]. Thus, culture has been identified as a factor that influences differences among nations in the handling of the pandemic [62]. In the current research, a similar comparative strategy is employed, with culture associated with the corporate communication of each army imprinting heterogeneity on the messages.

The second reference, with its innovative methodology, is relevant to include as a prospective study in section 5.4.

Please review the following lines:

5.4. Limitations, and Prospective Studies

Regarding limitations, it is important to note that the analysis dates correspond to the early stage of the Covid-19 pandemic, representing a specific and highly connected moment. Secondly, it is necessary to determine the existence of differences between temporal phases, as some studies suggest that during the first months of the pandemic, when social distancing measures were very strict, connectivity increased. Thirdly, the social media platform YouTube was omitted because during the data collection process, issues were identified that could jeopardize the reliability of the data. The received "likes" may be altered due to the presence of fake profiles that aim to troll cooperative profiles, so the research would benefit from using software like Graphex to study the community in detail and exclude profiles that generate only noise. In this sense, as the study relies on data from social media, there may be inherent biases or inaccuracies in this data, which should be acknowledged. Also, while the study focuses on major military powers, it is unclear whether these findings would extend to smaller nations or non-military organizations. Furthermore, it is necessary to take into account methodological considerations, as indicated by Wei Wei et al. [63]. When dealing with information from a post published on social networks, it is important to approach it from natural language processing (NLP) as a task of natural language understanding (NLU). In this regard, many methods overlook the importance of natural language comprehension. Hence, the need to employ classification methods called LSTM-SN (Long Short-Term Memory Recurrent Neural Network Fusion Social Network) is proposed [63].

The third research article adds valuable insights to section 5.1 as it demonstrates how social media serves as a barometer of reality.

Please review the following lines:

5.1. Differences between  social media platforms: Twitter, Instagram y Facebook

The most influential and long-standing social media platforms are Twitter, Instagram, and Facebook [46] [47] [14]. While all of these platforms involve dynamic interaction between users and profiles through KPIs such as likes and comments [50] [51], research conducted within the same historical context indicates differential behaviors, suggesting variations in the human needs they fulfill [46]. Other studies also highlight the ability of social networks as a thermometer of society, showcasing their influence and leadership in social processes [61].

Comment 4:

Unclear Implications: While the conclusion highlights the need for corporate communication to align with the emotional nature of posts, it would be beneficial to expand on the implications of your findings.

Response 4:

Dear reviewer, thank you very much for your comment. Following your suggestion, we have incorporated a final reflection (highlighted in intense yellow) to explain the implications of our findings. We hope to meet your expectations.

Please review the following lines:

5.3. Practical Applications

As practical applications of this research, it is highlighted the importance for military profiles to collaborate in the construction of the virtual community by paying attention to the language, emotional tone, and topics that their population reinforces through the use of likes. Thus, the principles developed by Hallahan [15] are proposed: a) engaging with the community by generating dialogues, b) promoting philanthropy, and c) showcasing social responsibility actions. Similarly, posts with positive sentiments that demonstrate positive leadership are more accepted by the population, as long as the nation is not involved in an armed conflict. However, the change in corporate communication management must start with dialogue, establishing trust and breaking cultural barriers in order to find common ground  [32]. The importance of building a sense of digital community in the Armed Forces is emphasized. This entails the strategic management of corporate communication, aligning the mission with the vision to connect synchronously with the thoughts and sentiments of society.

Limitations:

Comment 5:

Generalizability: While the study focuses on major military powers, it is unclear whether these findings would extend to smaller nations or non-military organizations.

Response 5:

Dear reviewer, thank you very much for your comment. We found the limitation you mentioned very interesting, and we have incorporated it into our study. We believe that this enhances our research and helps contextualize the results. We greatly appreciate your input, and we are confident that it has contributed to improving the quality of our work.

Please review the following lines:

5.4. Limitations, and Prospective Studies

Regarding limitations, it is important to note that the analysis dates correspond to the early stage of the Covid-19 pandemic, representing a specific and highly connected moment. Secondly, it is necessary to determine the existence of differences between temporal phases, as some studies suggest that during the first months of the pandemic, when social distancing measures were very strict, connectivity increased. Thirdly, the social media platform YouTube was omitted because during the data collection process, issues were identified that could jeopardize the reliability of the data. The received "likes" may be altered due to the presence of fake profiles that aim to troll cooperative profiles, so the research would benefit from using software like Graphex to study the community in detail and exclude profiles that generate only noise. In this sense, as the study relies on data from social media, there may be inherent biases or inaccuracies in this data, which should be acknowledged. Also, while the study focuses on major military powers, it is unclear whether these findings would extend to smaller nations or non-military organizations. Furthermore, it is necessary to take into account methodological considerations, as indicated by Wei Wei et al. [63]. When dealing with information from a post published on social networks, it is important to approach it from natural language processing (NLP) as a task of natural language understanding (NLU). In this regard, many methods overlook the importance of natural language comprehension. Hence, the need to employ classification methods called LSTM-SN (Long Short-Term Memory Recurrent Neural Network Fusion Social Network) is proposed [63].

Comment 6:

Bias in Social Media Data: As the study relies on data from social media, there may be inherent biases or inaccuracies in this data, which should be acknowledged. 

Response 6:

Dear reviewer, thank you very much for your comment. We found the limitation you mentioned very interesting, and we have incorporated it into our study.

Please review the following lines:

5.4. Limitations, and Prospective Studies

Regarding limitations, it is important to note that the analysis dates correspond to the early stage of the Covid-19 pandemic, representing a specific and highly connected moment. Secondly, it is necessary to determine the existence of differences between temporal phases, as some studies suggest that during the first months of the pandemic, when social distancing measures were very strict, connectivity increased. Thirdly, the social media platform YouTube was omitted because during the data collection process, issues were identified that could jeopardize the reliability of the data. The received "likes" may be altered due to the presence of fake profiles that aim to troll cooperative profiles, so the research would benefit from using software like Graphex to study the community in detail and exclude profiles that generate only noise. In this sense, as the study relies on data from social media, there may be inherent biases or inaccuracies in this data, which should be acknowledged. Also, while the study focuses on major military powers, it is unclear whether these findings would extend to smaller nations or non-military organizations. Furthermore, it is necessary to take into account methodological considerations, as indicated by Wei Wei et al. [63]. When dealing with information from a post published on social networks, it is important to approach it from natural language processing (NLP) as a task of natural language understanding (NLU). In this regard, many methods overlook the importance of natural language comprehension. Hence, the need to employ classification methods called LSTM-SN (Long Short-Term Memory Recurrent Neural Network Fusion Social Network) is proposed [63].

 

 

 

Comment 7:

The lack of meaningful conclusions: I did not find any conclusions, just a discussion.

Response 7:

Dear reviewer, we have added a dedicated conclusion section to provide a clearer overview of the main results.

Please review the following lines:

6. Conclusion

In summary, it is concluded that the profiles of the Armed Forces of major military powers do not fully align with the preferences of their virtual community. Military powers offer a highly technical and objective view of their reality, showcasing their professionalism and technical capabilities in line with military values. Despite significant differences observed among nations, in general, the virtual community demands positive, subjective, and emotionally diverse posts. In other words, human behavior on social networks requires adherence to a set of social norms that include slang and language from pop culture, as well as a relative "dramatization" of events, while also emphasizing pro-social and altruistic actions.

Minor issues:

Comment 8:

There are instances of non-English text in multiple places across the manuscript.

Response 8:

Dear reviewer, thank you very much for your comment. We have translated these texts into English. We thank him for his patience and we are sorry for the mistake made.

Comment 9:

Conclusion: Your study represents an interesting contribution to the research on social media usage and sentiment analysis during crises, particularly within the context of military institutions. By addressing these points in a Major revision, you could further strengthen your manuscript

Response 9:

Dear reviewer, thank you very much for your words. We have carried out all the comments that you and your colleagues have made to us. We appreciate your help in improving the quality of our work.

 

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The author has modified the manuscript according to the comments of the reviewer.

Reviewer 4 Report

The manuscript can be accepted for publication.