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.
The authors made all the comments, accepted
[# PeerJ Staff Note - this decision was reviewed and approved by Xiangjie Kong, a PeerJ Section Editor covering this Section #]
I have some concerns while reviewing the paper again; which are as follows:
1. The table's caption must be above the table, author adds, the caption below the tables e.g., in Table. 1 and 2.
2. The references are not uniform and not according to the journal format.
3. Minor typo mistakes need corrections.
Nil
Nil
Nil
The results need detailed explanation. Please address all the comments of the 2 reviewers.
No comment
No comment
Good
Not required
The manuscript, titled "Intent aware data augmentation by leveraging generative AI for stress detection in social media texts," is well developed; however, I have some concerns after a complete review of the paper, which are:
1. The abstract needs to be rewritten in significant writing, and the conclusion needs to include the percent improvement in the proposed work.
2. The significance or novelty of the study must be included in the introduction section of the proposed work.
3. The problem of limitations in the proposed work is missing; some points are included, but it would be beneficial to explicitly state the specific limitations faced, providing more context for readers unfamiliar with the background study.
4. The literature is missing the latest related work; authors need to include the state-of-the-art in the proposed work, i.e.,
a. Zeng, X., Gao, Z., Ye, Y., & Zeng, W. (2024). IntentTuner: An Interactive Framework for Integrating Human Intents in Fine-tuning Text-to-Image Generative Models. arXiv preprint arXiv:2401.15559.
b. Zeb, A., Din, F., Fayaz, M., Mehmood, G., & Zamli, K. Z. (2023). A systematic literature review on Robust Swarm intelligence algorithms in search-based software engineering. Complexity, 2023.
c. Islam, U., Al-Atawi, A. A., Alwageed, H. S., Mehmood, G., Khan, F., & Innab, N. (2024). Detection of renal cell hydronephrosis in ultrasound kidney images: a study on the efficacy of deep convolutional neural networks. PeerJ Computer Science, 10, e1797.
**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.
5. Figure 1 is very simple: how ChatGPT is used in the proposed work, and is it mentioned in the simulation?
6. The graphs are very simple; it would be better to compare your work to the state-of-the-art.
7. Minor typos and grammatical mistakes need correction before revision.
Need improvement.
Comments are given already.
The paper presents a well-structured investigation into stress detection, employing RoBERTa and intent-aware data augmentation. Methodology clarity and experimental results interpretation are commendable. Findings underscore the significance of intent-aware augmentation in stress detection. Limitations are addressed, and future directions are insightful.
I suggest the following changes:
1. The abstract is too wordy, I would suggest squeezing it to 150-170 words.
2. The background and related work section should be merged.
3. Motivation is missing.
4. Paper organization is missing.
5. The similarities should be reduced, I have seen a lot of phrases have been pasted directly without rephrasing.
6. Besides, the AI similarities should also be reduced.
7. In the Model Training Section, Mention the Training/Validation split to enhance reproducibility.
8. In Table 7, make the row with the best-performing proposed technique "Bold" to highlight.
9. Provide Full forms of Abbreviations Like BERT and RoBERTa, where first mentioned.
10. Consider reporting consistent performance metrics (e.g., F1 score) in the Related Works Section.
11. Mention the datasets used for RoBERTa and KC-NET while reporting the performance.
12. The results are not satisfactory, I would suggest revising the section with more details.
See the above comments
See the above comments
See the above comments
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.