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 paper has been revised to address all the problems identified in the review process
[# PeerJ Staff Note - this decision was reviewed and approved by Daniel S. Katz, a PeerJ Section Editor covering this Section #]
The paper has still some problems as follows:
1. Format problem, text does not have two ends aligned.
2. Reference about deep learning should be cited.
The author basically made revisions according to the comments of the reviewers.
Authors also need to be aware of the following issues.
1.CBOW is a commonly used model, and CBOW model using negative sampling has also been used by some people, which cannot be counted as their own innovation points, but can only be described in related work. The full name of the model should be given when it is first used. If there are innovations, highlight the differences from traditional methods.
2.There are some problems with the narration and the use of words in some sentences. Please check carefully.
no comment
no comment
no comment
It is good enough for this journal.
It is clear and good enough for this journal.
I can accept this version. It is good enough for this journal.
None
This paper proposes a network embedding learning algorithm combining network structure and node text features. The contrast experiment in this paper needs to be strengthened, and please check whether the relevant information of the affiliation is correct or not.
**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.
**PeerJ Staff Note:** Please ensure that all review and editorial comments are addressed in a response letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Alternatively, you should make your own arrangements to improve the language quality and provide details in your response letter. – PeerJ Staff
This paper proposes a network embedding learning algorithm combining network structure and node text features, which adds an attention mechanism to each word in node texts. But,The article has the following problems.
1.The address of the first work school provided by the author is problematic, and the author works for too many institutions, which makes people confused.
2.Abstract only describes the problem and the proposed new method, but does not point out the innovation of the new method and the main framework, the experimental summary is too simple.
3.The author shows that CBOW model is a commonly used model for solving word2vec, and what improvements and innovations have been made in it need to be clearly given and introduced in detail.
4.In introducing TAMNR Modeling, the author needs to show how attention is achieved, and the given figure 1 does not help the reader understand the design idea well.
5.The method proposed in this paper is based on attention mechanism, but there is no such algorithm in the comparison experiment, which cannot show the effectiveness of its algorithm. Please add 1-2 latest related algorithms for comparison experiment.
no comment
The method proposed in this paper is based on attention mechanism, but there is no such algorithm in the comparison experiment, which cannot show the effectiveness of its algorithm. Please add 1-2 latest related algorithms for comparison experiment.
no comment
The logic is good, but the word should be in accordance with the language criterion.
1. Why did you use these three open citation network datasets for testing? The authors should explain more about the selection of the datasets.
2. The article needs more experiments to verify that the new approach can be applied to more domains.
The authors need to discussion more about embedding.You can refer to the research article as follows, which might be helpful to you:
Zhang, C., Shang, K., & Qiao, J. (2021). Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Prediction. Complex., 2021,
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.