Sustainability-Driven Green Innovation: Revolutionising Aerospace Decision-Making with an Intelligent Decision Support System

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

 

 

 I think the authors have written an interesting paper dealing with an important topic. The overall representation of this paper is technically sound. I have, however, a few comments and suggestions for them:

-The given abstract lacks clarity and precision in terms of reflecting the paper's content and findings. It is therefore recommended that the abstract be carefully rewritten to effectively demonstrate the necessity, novelty, and contribution of the research, as well as highlight its major findings.

-The present literature survey is deemed insufficient. The authors are encouraged to conduct a more extensive review of the relevant literature to enhance the current state of their work. It is worth noting that several noteworthy research articles in this field have not been taken into account in the present form. Therefore, the inclusion of some recent articles published in the year 2022-23 is recommended to enrich the literature.

-The main objectives of the research are defined at the introduction of the study. The authors described the study problem and research questions, the importance of the study, and the hypotheses as well.

 -The methodology contains a correct description of the methods applied and is well documented and supported.

 

-All the tables and figures are clear, understandable, and relevant; sources are well indicated in each case.

-Regrettably, neither a conceptual comparison with existing approaches nor any discussion about the benefits and drawbacks of the new approach has been put forth. Therefore, discussions and comparative analyses ought to be incorporated. It is imperative to compare the proposed method with the literature.

 

-A section namely “Conclusions” must be incorporated. The conclusion part should contain the author’s main findings; and contribution as well as it should give a direction for future researchers. The key contributions are not highlighted in the present manuscript.

Author Response

Comment: I think the authors have written an interesting paper dealing with an important topic. The overall representation of this paper is technically sound. I have, however, a few comments and suggestions for them.

Response: We appreciate your positive feedback. The point-by-point response is discussed below:

Comment: The given abstract lacks clarity and precision in terms of reflecting the paper's content and findings. It is therefore recommended that the abstract be carefully rewritten to effectively demonstrate the necessity, novelty, and contribution of the research, as well as highlight its major findings.

Response: We appreciate your feedback. The abstract has been rewritten to enhance its clarity and precision in reflecting the paper's content, data collection, findings, necessity, novelty, and contributions. Also, the language editing of article from a professional language editing company has further improved the quality of the abstract and the article in general.  

Comment: The present literature survey is deemed insufficient. The authors are encouraged to conduct a more extensive review of the relevant literature to enhance the current state of their work. It is worth noting that several noteworthy research articles in this field have not been taken into account in the present form. Therefore, the inclusion of some recent articles published in the year 2022-23 is recommended to enrich the literature.

Response: We appreciate your feedback regarding our literature review. In response to your suggestions, we have expanded and refined our literature review section to incorporate recent publications from the years 2020, 2021, and 2022.

Comment: The main objectives of the research are defined at the introduction of the study. The authors described the study problem and research questions, the importance of the study, and the hypotheses as well.

Response: We appreciate your positive feedback.

Comment: The methodology contains a correct description of the methods applied and is well documented and supported.

Response: We appreciate your positive feedback.

Comment: All the tables and figures are clear, understandable, and relevant; sources are well indicated in each case.

Response: We appreciate your positive feedback.

Comment: Regrettably, neither a conceptual comparison with existing approaches nor any discussion about the benefits and drawbacks of the new approach has been put forth. Therefore, discussions and comparative analyses ought to be incorporated. It is imperative to compare the proposed method with the literature.

Response: We appreciate your valuable feedback on our manuscript. In response, we have addressed the absence of a conceptual comparison and discussions on the benefits and drawbacks of our proposed approach. Specifically, we have extended the findings section to include a comparative analysis with existing methods, highlighting the strengths and limitations of our approach. Additionally, a dedicated section now explicitly compares our methodology with relevant literature, offering a comprehensive understanding of its novelty

Comment: A section namely “Conclusions” must be incorporated. The conclusion part should contain the author’s main findings; and contribution as well as it should give a direction for future researchers. The key contributions are not highlighted in the present manuscript.

Response: We have addressed your suggestion by incorporating a dedicated "Conclusions" section in the manuscript. This section now highlights the main findings and contributions of our research while also providing direction for future researchers. Your input has been invaluable in improving the structure and content of our paper.

Reviewer 2 Report

Comments and Suggestions for Authors

This paper provides surveys on online references regarding the aerospace industry. But I think the survey is not done systematically and the method used in scrapping online data is not well structured. Also, I find that the title does not match with the content of the paper and a bit overclaimed. The detail of my comments are as follows.

1. Abstract. the abstract is too general. It does specifically represent what has been done and what exactly the significant findings of this work. 

2. Introduction. I cannot find, what is exactly the problem that the authors want to explore in this work. I cannot find something new in the description regarding the aerospace industry. The current problem in this industry is not presented. AI is widely used in the aerospace industry. Furthermore, from a theoretical point of view, the authors do not provide the research edge in this area. The authors provide 5 research questions, however, no supporting evidence from current research is provided.

3. Literature review. View literature is reviewed and some of them are quite obsolete (more than 20 years ago!).   More comprehensive, critical, and systematic reviews should be done. From this literature review, the authors should point out the research gap and define the need for this work. 

4. Methods. This section should clearly describe the procedures used in this research. Unfortunately, the steps in doing this work are unclear and less systematic. There are a lot of machine learning methods that can be used in scrapping online data. The authors can choose one of them. I am not sure that the search query is correct to answer the objective of this research (?). Too many technical are provided in this section and unfortunately, I cannot find the main "content" of this work. 

5. Discussion. It is unclear regarding the statement of "the concept of green innovation is of significant importance in today's world......". Where did this conclusion come from? I cannot find any work in this paper that supports this claim. All findings presented are normative and commonsense. 

In conclusion, unfortunately, I could not see any significant contribution of this work both in practical application and theoretical point of view.

 

 

Comments on the Quality of English Language

English language should be improved.

Author Response

Comment: This paper provides surveys on online references regarding the aerospace industry. But I think the survey is not done systematically and the method used in scrapping online data is not well structured. Also, I find that the title does not match with the content of the paper and a bit overclaimed. The detail of my comments are as follows.

Response: We appreciate your comments. Our point-by-point response is discussed below.

Comment: Abstract. the abstract is too general. It does specifically represent what has been done and what exactly the significant findings of this work.

Response: We appreciate your feedback. The abstract has been rewritten to enhance its clarity and precision in reflecting the paper's content, data collection, findings, necessity, novelty, and contributions. Also, the language editing of article from a professional language editing company has further improved the quality of the abstract and the article in general. 

Comment: Introduction. I cannot find, what is exactly the problem that the authors want to explore in this work. I cannot find something new in the description regarding the aerospace industry. The current problem in this industry is not presented. AI is widely used in the aerospace industry. Furthermore, from a theoretical point of view, the authors do not provide the research edge in this area. The authors provide 5 research questions, however, no supporting evidence from current research is provided.

Response: Thank you for your comment. We've enhanced the introductory section to better articulate the justification and motivation behind this study. For example, the following paragraph is rephrased and revised.

“As the aerospace industry continues to evolve and grow, especially after the launch of SpaceX by Elon Musk in 2002, there is an increasing need for intelligent decision-making systems that can help streamline processes and improve overall efficiency. Moreover, the recent advancements seen in the shape of the proliferation of the artificial intelligence ap-plications, tools, and systems, the need for developing a new intelligent decision support system (IDSS) was felt more recently. This is where an improved version of IDSS comes in. By harnessing the power of AI and ML, this system can revolutionise how aerospace professionals make decisions, providing real-time insights and recommendations to help identify problems and opportunities before they become critical. Whether one is working in aircraft design, logistics or any other area in the aerospace field, the IDSS can help one stay ahead of the curve and make better, more informed decisions every step of the way.

The aerospace sector, characterised by a dynamic landscape, has embraced decision support systems (DSSs) as instruments for discerning and tracking emergent technological paradigms poised to shape its trajectory. These systems are pivotal in steering strategic resource allocation decisions by corporations and government entities. The present dis-course on such systems is focused on delineating their conceptual underpinnings, particularly in the context of foresight research within the aerospace industry. Our research considered burgeoning trends and technologies within space to assess their imminent and transformative potential. Following this evaluation, a structured framework was devised to monitor and manage the trajectories of these nascent paradigms. Central to this endeavour was the imperative to furnish an array of stakeholders with cogent insights requisite for informed strategic determinations.”

Comment: Literature review. View literature is reviewed and some of them are quite obsolete (more than 20 years ago!).   More comprehensive, critical, and systematic reviews should be done. From this literature review, the authors should point out the research gap and define the need for this work.

Response: We appreciate your constructive feedback regarding our literature review. In response to your suggestions, we have significantly refined the literature review section to incorporate recent publications from the years 2020, 2021, and 2022. Besides, the introduction section has been revised to discuss the research gaps and the need for this study.

Comment: Methods. This section should clearly describe the procedures used in this research. Unfortunately, the steps in doing this work are unclear and less systematic. There are a lot of machine learning methods that can be used in scrapping online data. The authors can choose one of them. I am not sure that the search query is correct to answer the objective of this research (?). Too many technical are provided in this section and unfortunately, I cannot find the main "content" of this work.

Response: We thank the reviewer for their valuable input. In our paper, we introduce the Greedy Summariser method, which outperforms traditional abstracting techniques across various metrics. This method leverages TFIDF to assess sentence importance and follows a systematic, step-by-step process to generate a summary. This approach ensures the thorough extraction of relevant data, thereby enhancing decision support in space technology. We have also revised the section to provide a clearer and more systematic description of our methodology. Additionally, we have carefully reconsidered the appropriateness of the search query to align with the research objectives. Your comments have been instrumental in improving the clarity and effectiveness of our methods section.

Comment: Discussion. It is unclear regarding the statement of "the concept of green innovation is of significant importance in today's world......". Where did this conclusion come from? I cannot find any work in this paper that supports this claim. All findings presented are normative and commonsense.

Response: We thank you for identifying this and we are sorry for this oversight. We have cited the relevant study in the discussion section to support this claim.

Comment: In conclusion, unfortunately, I could not see any significant contribution of this work both in practical application and theoretical point of view.

Response: The discussion and conclusion sections have been revised to provide a better understanding of the theoretical and managerial implications of the study.

Reviewer 3 Report

Comments and Suggestions for Authors

The paper aims to introduce an Intelligent Decision Support System (IDSS) for the aerospace industry, focusing on sustainability and green innovation. It outlines the conceptual framework, data collection methods, and preprocessing techniques and discusses research questions related to safety, efficiency, and environmental impact.

Paper Organization:

The paper is organized into several key sections, including Introduction, Methods, Preprocessing, and Discussions. While the paper covers a broad range of topics, the organization could be improved for better flow and readability. The "Discussions" section, for example, could be more comprehensive and better organized to guide the reader through the paper's findings and implications.

Technical Strengths:

1. Interdisciplinary Approach: The paper successfully integrates concepts from artificial intelligence, aerospace engineering, and environmental science, making it a truly interdisciplinary work.

2. Methodological Rigor: The paper outlines a detailed methodology for data collection and preprocessing, including the use of web crawlers, academic library APIs, and various algorithmic techniques like TF-IDF, YAKE, and NER.

3. Theoretical Depth: The "Discussions" section provides valuable insights into the effectiveness of classification models and acknowledges the limitations of the study.

4. Transparency: The paper is transparent about its limitations, particularly in the "Discussions" section.

Technical Weaknesses:

1. Lack of Empirical Validation: The paper is largely conceptual and lacks empirical data to substantiate its claims.

2. Narrow Analytical Scope: The paper focuses solely on keyword-based data analysis, limiting its analytical depth.

3. Incomplete Sections: Some sections, like the "Search Engine Data" in the "Methods" section, appear to be incomplete, which could be a significant oversight.

4. Lack of Metrics: The paper does not provide metrics or KPIs to evaluate the effectiveness of the proposed methods or the limitations discussed.

Proposed Technical Method:

The paper proposes an IDSS that leverages various data collection methods and preprocessing techniques. The methodology is technically sound but lacks empirical validation. The use of standard algorithmic techniques like TF-IDF, YAKE, and NER adds technical rigor but needs to be validated with real-world data.

Research Questions:

The paper poses research questions related to safety, efficiency, and environmental impact in the aerospace industry. However, it does not provide empirical data to answer these questions fully.

Suggestions to the Authors:

1. Empirical Studies: I strongly recommend that you include empirical studies to validate the theoretical and methodological aspects discussed in the paper with the other methods (baseline models) in order to prove the proposed method is validity.

2. Expand Analytical Scope: Consider expanding the scope of your analysis methods beyond keyword-based techniques.

3. Complete Incomplete Sections: Complete all incomplete sections to provide a full picture of your methodology and findings.

4. Inclusion of Metrics: Include specific metrics or KPIs that could be used to evaluate the theoretical implications and limitations discussed. Please add AUC diagrams and confusion matrixes.

5. Improve Paper Organization: Improve the paper's organization for better flow and readability.

6. Contextual Analysis for Tables: Include a contextual analysis of the data presented in the tables.

7. Interpretation of Results: Include an interpretation of the results to offer insights into their implications for the aerospace industry.

8. Address Research Questions: Make sure to provide empirical or theoretical answers to all the research questions posed in the paper.

9. Computational Complexity: Include information about the computational complexity of the algorithms used, which is crucial for real-world applications.

10. Ethical Considerations: Given the increasing importance of ethics in AI and technology, a separate section discussing the ethical implications would add significant value to the paper. (One of your research questions)

The paper has the potential to make a significant contribution to the field but requires substantial revisions to address its limitations. My recommendation is "Major Revisions" before it can be considered for publication.

By addressing these points, the paper could serve as a comprehensive guide for the development and implementation of an IDSS in the aerospace industry, with a strong focus on sustainability and green innovation.

 

Comments on the Quality of English Language

It needs only a minor improvement.

Author Response

Comment: The paper aims to introduce an Intelligent Decision Support System (IDSS) for the aerospace industry, focusing on sustainability and green innovation. It outlines the conceptual framework, data collection methods, and preprocessing techniques and discusses research questions related to safety, efficiency, and environmental impact.

Response: We appreciate your positive feedback.

Comment: The paper is organized into several key sections, including Introduction, Methods, Preprocessing, and Discussions. While the paper covers a broad range of topics, the organization could be improved for better flow and readability. The "Discussions" section, for example, could be more comprehensive and better organized to guide the reader through the paper's findings and implications.

Response: We appreciate your valuable feedback. We acknowledge that there is room for improvement in the organization of the paper to enhance overall flow and readability. We have carefully considered your suggestion and have taken steps to enhance the "Discussions" section, ensuring it offers a comprehensive and well-organized overview of the paper's findings and their implications.in addition, we have also developed and added a dedicated ‘conclusions section’ in the revised manuscript. 

Comment: Interdisciplinary Approach: The paper successfully integrates concepts from artificial intelligence, aerospace engineering, and environmental science, making it a truly interdisciplinary work.              

Response: We appreciate your positive feedback.

Comment: Methodological Rigor: The paper outlines a detailed methodology for data collection and preprocessing, including the use of web crawlers, academic library APIs, and various algorithmic techniques like TF-IDF, YAKE, and NER.         

Response: We appreciate your positive feedback.

Comment: The "Discussions" section provides valuable insights into the effectiveness of classification models and acknowledges the limitations of the study.       

Response: We appreciate your positive feedback.

Comment: The paper is transparent about its limitations, particularly in the "Discussions" section.

Response: We appreciate your positive feedback.

Comment: Lack of Empirical Validation: The paper is largely conceptual and lacks empirical data to substantiate its claims.

Response: We have enhanced the intro, literature review, methods, results, and the discussion sections and providing more empirical evidence to justify the study motivation and contributions.

Comment: The paper focuses solely on keyword-based data analysis, limiting its analytical depth.

Response: The proposed semantic citation map algorithm is based on the approaches of graph algorithms and the formal structure of scientific documents, especially the presence of links between documents in the form of citations and the ability to identify keywords that can fully describe the semantic meaning of the document.

Comment: Some sections, like the "Search Engine Data" in the "Methods" section, appear to be incomplete, which could be a significant oversight.

Response: Thank you identifying this. We have reviewed the sub-section “Search Engine Data” carefully and could not identify any missing information. Nonetheless, we sent the revised manuscript to professional language editing, and we believe that this has improved the quality of the language which might have resolved this query.

Comment: The paper does not provide metrics or KPIs to evaluate the effectiveness of the proposed methods or the limitations discussed.

Response: We have revised the limitations section to discuss the issues concerning the new suggested system i.e., IDSS.

Comment: The paper proposes an IDSS that leverages various data collection methods and preprocessing techniques. The methodology is technically sound but lacks empirical validation. The use of standard algorithmic techniques like TF-IDF, YAKE, and NER adds technical rigor but needs to be validated with real-world data.

Response: To address this concern, we have revised the paper to include empirical validation using real-world data. In this paper, a new method called GreedySummariser is introduced, which outperforms traditional abstracting methods on test data based on various synthetic metrics. The method is based on calculating the importance of sentences using the TF-IDF (Term Frequency-Inverse Document Frequency) statistical measure. TF-IDF is computed using equations (1), where tf represents the term frequency, idf represents the inverse document frequency, t is the number of terms in the document, d is the length of the paper, N is the number of copies, and df is the number of documents containing a term. This validation will involve applying the proposed methodology to relevant datasets and evaluating its performance against established benchmarks or using appropriate evaluation metrics. By conducting empirical validation, we aim to provide concrete evidence of the effectiveness and practicality of our IDSS approach.

Comment: The paper poses research questions related to safety, efficiency, and environmental impact in the aerospace industry. However, it does not provide empirical data to answer these questions fully.

Response: It's crucial to acknowledge that the absence of empirical data to answer the research questions related to safety, efficiency, and environmental impact in the aerospace industry is a limitation of the paper. While the paper may outline these research questions and propose hypotheses or theoretical models, the absence of empirical data means that the findings and conclusions presented may lack the necessary support for their validity.

Comment: I strongly recommend that you include empirical studies to validate the theoretical and methodological aspects discussed in the paper with the other methods (baseline models) in order to prove the proposed method is validity.               

Response: We have added the recent studies in almost all the sections to provide the better explanation of the concept and also to validate the theoretical and methodological aspects.

Comment: Consider expanding the scope of your analysis methods beyond keyword-based techniques.

Response: Thank you for your suggestion. In addition to keyword-based techniques like TF-IDF, we have incorporated other advanced analysis methods to provide a more comprehensive analysis. This paper introduces the GreedySummariser method, which outperforms traditional abstracting methods on test data based on various synthetic metrics. It is based on calculating the importance of sentences through a common statistical measure, TF-IDF.

Comment: Complete all incomplete sections to provide a full picture of your methodology and findings.

Response: We have diligently addressed your feedback and included more comprehensive descriptions in the methodology section. This effort is aimed at providing a holistic understanding of our research methodology and findings. Besides, the professional language editing of the paper has further improved the quality of the revised manuscript.

Comment: Include specific metrics or KPIs that could be used to evaluate the theoretical implications and limitations discussed. Please add AUC diagrams and confusion matrixes.               

Response: We have revised the limitations section to discuss the issues concerning the new suggested system i.e., IDSS. Also, we have added the figure 4, 5, and 6 to ensure the inclusion of AUC diagrams and confusion matrices in the revised paper.

Comment: Improve the paper's organization for better flow and readability.                     

Response: We appreciate your positive feedback. We sent the revised manuscript for professional language editing, which we believe has improved the flow and readability of the article.

Comment: Include a contextual analysis of the data presented in the tables.                     

Response: Based on the content provided, the data collected for the Intelligent Decision Support System (IDSS) from open sources includes news articles and posts from social media platforms such as Vk.com, Instagram, Facebook, and Twitter. The data collection period spanned from January 1, 2016, to November 5, 2021 as explained in section 3.2.3. Data collected from public sources.

Comment: Include an interpretation of the results to offer insights into their implications for the aerospace industry.      

Response: The article introduces an Intelligent Decision Support System (IDSS) specifically designed for the aerospace technology sector. The IDSS harnesses the power of artificial intelligence (AI) algorithms to extract, process, and analyze data from various sources. Its primary purpose is to provide valuable insights that facilitate informed decision-making within the aerospace industry.

Comment: Make sure to provide empirical or theoretical answers to all the research questions posed in the paper.

Response: We have revised the findings and discussion sections to better align them with the suggested research questions.

Comment: Include information about the computational complexity of the algorithms used, which is crucial for real-world applications.

Response: The algorithm was tested on an open dataset collected from various online sources as part of the "publication activity monitoring" task. After data cleaning and transformation into a machine-readable format, the dataset comprised 5,762 articles. The subsequent data transformation in the algorithm's processing involved creating an "article-article" adjacency matrix based on the reference links obtained from the "List of Used Sources" section. The TF-IDF, YAKE, and NER algorithms were utilized to extract common keywords for modeling thematic connections between scientific and technical publications. As a result of the aforementioned transformations, a dataset was generated with 26,066 rows and columns, where "key_1" represents the identifier of the source article, "key_2" represents the identifier of the target article, "keyword_1" and "keyword_2" represent the keywords of the source and target articles, "title_1" and "title_2" represent the titles of the source and target articles, and "abstract_1" and "abstract_2" represent the abstracts of the source and target articles.

Comment: Given the increasing importance of ethics in AI and technology, a separate section discussing the ethical implications would add significant value to the paper (One of your research questions).

Response: As suggested, we have now added a separate sub-section 2.3 discussing the use of AI and growing ethical issues.

Round 2

Reviewer 3 Report

Comments and Suggestions for Authors

Dear author(s), Thank you for your collaboration and support. After the second revision, I found out that your manuscript was greatly improved. I hope my comments helped you improve its quality and better reflect its originality. I want to thank you one more time.