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.
I thank the authors for their efforts to improve the work. The current version can be accepted.
[# PeerJ Staff Note - this decision was reviewed and approved by Jyotismita Chaki, a PeerJ Section Editor covering this Section #]
The author has already made revisions based on the comments, and I suggest accepting the publication of this article.
no comment
no comment
no comment
Based on the comments of the reviewers, the work is interesting. However, it needs further revision in writing, experiments, etc. Please refer to the comments and revise the article accordingly.
Reviewer 3 has requested that you cite specific references. You may add them if you believe they are especially relevant. If you do not include them, this will not influence my decision.
**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, 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.
NA
NA
NA
NA
This paper propse a new method which is structural-topic aware and based on deep neural network. It's ttheoretical basis is reasonable with relative clear definitions of all terms and detailed proofs. The downside is that the description of STDNN is not sufficient: which backbone of deep neural network is adopt ? how does NMF selection work in Figure 2 ?
Futher experiment are suggested: more than two dataset and more comprehensive comparsion of computation cost.
no comment
no comment
1、The paper is poorly readable and the language needs major revision.
2、The introduction lacks the description of the research significance and application area as well as the structure is not completed, please making major revisions.
3、The references are old in the paper, please replacing the references.
4、The writing of the related work section is logically confusing, please making major revisions.
5、Figure 2 fails to clearly depict the framework proposed in the paper and adding a table of symbol meanings.
6、In section of the method, the MLP module is not described clearly.
7、please Summary part is carefully rewritten.
1、The baseline model selected in this paper is old and lacks the latest benchmark model.
2, In the experimental, please adding ablation experiments, visualization analysis, parameter sensitivity analysis and other experiments.
3、The use of one evaluation criterion in this paper is weakly persuasive, please adding other evaluation criteria.
no comment
The following important articles are missing from the references:
**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.
1) "Dynamic topic modeling via self-aggregation for short text streams." Peer-to-peer Networking and applications 12 (2019): 1403-1417.
2) "A semantic modeling method for social network short text based on spatial and temporal characteristics." Journal of computational science 28 (2018): 281-293.
3) "A user-based aggregation topic model for understanding user’s preference and intention in social network." Neurocomputing 413 (2020): 1-13.
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.