All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Two reviewers have commented positively on your revision, and I can therefore accept this contribution for publication in PeerJ Computer Science.
[# PeerJ Staff Note - this decision was reviewed and approved by Maurice ter Beek, a PeerJ Section Editor covering this Section #]
no comment
no comment
no comment
It can be accepted
no comment
no comment
no comment
no comment
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors agree that they are relevant and useful.
**PeerJ Staff Note:** Please ensure that all review, editorial, and staff comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
This article proposes a Decision Support Framework for Optimizing Career Path Prediction. It combined the interval-valued spherical fuzzy MARCOS and MCGDM, and then has some interesting idea.
.
.
Also, it has the following question:
1.The authors should prove the advantage of the proposed method:interval-valued spherical fuzzy MARCOS and MCGDM in the abstract and introduction.
2.In the introduction, the authors should introduce the MCGDM of Career Path Prediction, and compare them with your work.
3. In a group decision making problem, it usually exist interference or conflict between decision makers. But this article does propose new model to resolve this issue such as: Social network group decision making: Characterization, taxonomy,challenges and future directions from an AI and LLMs perspective. Information Fusion 120 (2025) 103107; A transformation method of non-cooperative to cooperative behavior by trust propagation in social network group decision making, DOI:0.1109/TFUZZ.2025.3557904.
4. In Section 6, the authors should add detail and actual background of the case.
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors are in agreement that they are relevant and useful.
REVIEW REPORT
Manuscript Title: A Decision Support Framework for Optimizing Career Path Prediction and Vocational Mobility of College Graduates
Manuscript Number: 117700
Journal: PeerJ Computer Science
This manuscript addresses an important and contemporary issue—career path prediction and vocational mobility (VM) of college graduates—through a novel application of the interval-valued spherical fuzzy MARCOS (IVSF-MARCOS) technique in a multi-criteria group decision-making (MCGDM) setting. The integration of fuzzy logic to handle uncertainty in VM assessment is well-motivated, and the proposed model shows theoretical promise. However, the manuscript requires major revisions before it can be considered for publication due to issues with language clarity, technical exposition, validation robustness, and presentation quality. Some comments are suggested to improve the quality of this paper.
Suggestions for Improvement:
1. Rewrite the abstract and introduction to clearly articulate the research problem, objective, and contribution. Include a clearer objective at the end of the introduction.
2. Table 14 compares methods but lacks citations or empirical support for the ratings (e.g., "High" vs. "Medium"). Reference studies or benchmarks justifying these ratings.
3. Please recheck the numbering of all tables. Multiple tables are currently labeled as 'Table 1', which creates confusion. Kindly correct the numbering to ensure each table has a unique and sequential identifier.
4. The paper uses many abbreviations, please make sure that every abbreviation is explained the first time it appears. This is not always the case, e.g., abbreviations like IVSFWA used in the manuscript but this is not explained before. It is recommended to define all abbreviations upon first use and include a list of abbreviations in a table after the abstract or before Section 1.
5. While the introduction cites relevant works, include a deeper comparison with related works to position your model within the existing body of research. Emphasize the specific limitations in existing models that your work addresses.
6. Expand the literature review by including more recent research on fuzzy set, spherical fuzzy set, interval-valued spherical fuzzy set, multi-criteria group decision-making and their applications in various domains, to ensure the literature review reflects the latest developments in the field.
7. I strongly recommend double-checking all the symbols and formulas to ensure accuracy in indices, notation, and conceptual consistency. To improve readability, consider adding a table summarizing all mathematical symbols and their definitions used in the manuscript.
8. Please recheck all references to ensure they are written correctly and include complete information. Some references are incomplete. For instance, reference [9] is missing the publisher name, volume number, and page range. Kindly verify each entry against the original sources and update any missing details (e.g., DOIs, journal abbreviations, or publication dates) to align with the journal’s citation style guidelines.
The paper makes a significant theoretical contribution and has strong potential for real-world applications but requires significant revision in terms of language, structure, and typesetting before it can be accepted for publication.
1. The IVSF-MARCOS method is described mathematically but lacks a clear, intuitive explanation for non-experts. Add a brief plain-language summary of the method's steps and purpose.
2. The roles of decision-makers are mentioned but not justified (e.g., why five decision-makers?). Explain how the number and expertise of decision-makers were determined.
3. The IVSF-MARCOS method is described mathematically but lacks a clear, intuitive explanation for non-experts. Add a brief plain-language summary of the method's steps and purpose.
4. The roles of decision-makers are mentioned but not justified (e.g., why five decision-makers?). Explain how the number and expertise of decision-makers were determined.
5. The manuscript claims high precision but does not discuss potential biases (e.g., decision-maker subjectivity). Address limitations explicitly, such as expert bias or data quality issues.
6. Sensitivity analysis is mentioned but not thoroughly explained (e.g., how scenarios were generated). Detail the methodology for sensitivity testing (e.g., weight variation ranges).
7. The weights assigned to experts are arbitrary and lack explanation or validation. To strengthen this aspect, please reference and align your approach with established methodologies that justify expert weight aggregation and linguistic variable modeling for decision matrices.
The proposed IVSF-MARCOS model demonstrates strong internal validity through rigorous sensitivity analysis and expert consensus, ensuring robustness against input variations. External validity is supported by the model's alignment with real-world career mobility trends, though generalizability may require further testing across diverse labor markets. Limitations include potential expert bias and static criteria, suggesting future work should incorporate dynamic, real-time labor data.
1. The introduction is repetitive. The research gap, objectives, and contributions are stated multiple times, leading to redundancy. The authors should consolidate these sections to present a more streamlined and impactful introduction.
2. The literature review is presented as a list of summaries rather than a critical analysis.
3. The quality of the figures is poor.
1. The paper lacks justification for choosing the complex IVSF-MARCOS method. The paper provides a detailed history of fuzzy sets and a step-by-step algorithm, but never explains why this specific level of complexity is necessary for this problem compared to simpler, more established, and more transparent methods
2. The study claims its contribution is applying the IVSF-MARCOS method to the domain of career development. While applying existing techniques to new domains can be valuable, the novelty seems limited. The work reads more like an application paper in operations research or decision science than a fundamental computer science contribution.
1. The final ranking of career paths is the central output of the framework. According to Table 13, the top-ranked career is A12 (Sports and Recreation), while the lowest-ranked career is A6 (Information Technology). This result is extraordinary and counterintuitive. A decision-support framework that suggests IT is the worst possible career path for a college graduate requires an exceptional level of justification. The authors present this ranking in the "Result Discussion" section without any comment on its surprising nature. They simply state the ranks as fact. This is a major scientific omission.
2. The comparison provided in Table 14 is a qualitative self-assessment that favorably positions IVSF-MARCOS against other MCDM methods. This is not a rigorous, empirical comparison. To validate the superiority of their chosen method, the authors would need to apply several of these methods to the same dataset and compare the outcomes, discussing the similarities, differences, and potential reasons for any discrepancies.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.