E3W—A Combined Model Based on GreedySoup Weighting Strategy for Chinese Agricultural News Classification
Round 1
Reviewer 1 Report
Paper deals with important task. The authors proposed a classification model E3W based on GreedySoup weighted strategy and multi-model combination for Chinese agricultural news classification.
Paper has great practical value.
Experimental secion is good.
Suggestions:
1. The abstract section should be extended using more clearly the motivation of this paper. Only this sentence “The explosion of agricultural news has made accurate access to agricultural news difficult” isn’t informative
2. It would be good to add the remainder of this paper (structure) at the end of the Introduction section
3. The quality of data is very importan for such research. He authors write that “The dataset constructed in this paper was obtained from agricultural news websites” But please argue is such sources of data is reliable for your research.
4. The authors should provide a link to open access repository with the dataset used for modeling
5. The authors should add all optimal parameters for all investigated methods
6. The conclusion section should be extended using: 1) numerical results obtained in the paper; 2) limitations of the proposed approach; 3) prospects for future research.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
I thank the authors for taking into account the comments of reviewers. Please note some comments related to formatting: 1) the caption of Figure 2 is on the next page, 2) textCNN -> TextCNN, 3) duplicated sentence: "At the input encoding layer, the text of the input text is masked by ERNIE, embedded, and finally fed into the transformer for encoding", 4) you use "BiGRU" in the text and "BIGRU" in Figure 4. The paper also needs moderate language checking.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
This paper has done a kind of comparative study of models inspired by group of CNN models(LSTM,GRU ect.) for Chinese Agricultural News Classification. As this is a comparative study and there is nothing wrong doing a comparative study, therefore, I would suggest to compare your models with as much as possible existing models(even if possible with existing ML models). This paper needs revision.
1) Word cloud representation is needed here .
2) Data pre processing part is not sufficient, talk more about the data that you considered here.
3) Why not Glove? why only word2vector word embedding?? please mention the reason in the introduction section itself.
4) You have completely missed the CNNs and other deep learning models' representation equations. Kindly provide them. Can't find any equations???
5) Table 4 is confusion matrix ??where are the obtained values of CM for your models?
6) Discussion part has to be kept before conclusion where you have to analyze the detail of the outcomes of your proposed models.
7) Compare more existing models such as even with conventional ML models like XGBoost, RF, LR, NB ect.
8) Write algorithms for your proposed model(pseudocode).
9) The term "GreedySoup weighted" need to be justified, why such term in the title ? If your proposed model using the greedy strategy then please try to provide PROOF of the following two points of Greedy
1. Greedy-choice property: A global
optimum can be arrived at by selecting a
local optimum.
2. Optimal substructure: An optimal solution to the problem contains an optimal solution to subproblems.
10) You must cite the following papers.
a) Li, J., Li, G., Liu, M., Zhu, X., & Wei, L. (2022). A novel text-based framework for forecasting agricultural futures using massive online news headlines. International Journal of Forecasting, 38(1), 35-50.
b) Turki, T., & Roy, S. S. (2022). Novel Hate Speech Detection Using Word Cloud Visualization and Ensemble Learning Coupled with Count Vectorizer. Applied Sciences, 12(13), 6611.
c) Lai, C. M., Chen, M. H., Kristiani, E., Verma, V. K., & Yang, C. T. (2022). Fake News Classification Based on Content Level Features. Applied Sciences, 12(3), 1116.
d) Roy, S. S., Goti, V., Sood, A., Roy, H., Gavrila, T., Floroian, D., ... & Mohammadi-Ivatloo, B. (2014). L2 regularized deep convolutional neural networks for fire detection. Journal of Intelligent & Fuzzy Systems, (Preprint), 1-12.
e) Varlamis, I., Michail, D., Glykou, F., & Tsantilas, P. (2022). A Survey on the Use of Graph Convolutional Networks for Combating Fake News. Future Internet, 14(3), 70.
f) Biswas, R., Vasan, A., & Roy, S. S. (2020). Dilated deep neural network for segmentation of retinal blood vessels in fundus images. Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 44(1), 505-518.
g) Keya, A. J., Wadud, M. A. H., Mridha, M. F., Alatiyyah, M., & Hamid, M. A. (2022). AugFake-BERT: Handling Imbalance through Augmentation of Fake News Using BERT to Enhance the Performance of Fake News Classification. Applied Sciences, 12(17), 8398.
h) Aldhyani, T. H., Alsubari, S. N., Alshebami, A. S., Alkahtani, H., & Ahmed, Z. A. (2022). Detecting and analyzing suicidal ideation on social media using deep learning and machine learning models. International journal of environmental research and public health, 19(19), 12635.
i) Roy, Sanjiban Sekhar, Sanda Florentina Mihalache, Emil Pricop, and Nishant Rodrigues. "Deep convolutional neural network for environmental sound classification via dilation." Journal of Intelligent & Fuzzy Systems Preprint (2022): 1-7.
j) Roy, S. S., Rodrigues, N., & Taguchi, Y. (2020). Incremental dilations using CNN for brain tumor classification. Applied Sciences, 10(14), 4915.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors did a lot of improvements.
Paper can be accepted in current form.
Author Response
Dear reviewer
Thank you very much for your approval of this paper. In follow-up, we have made the dataset for this paper publicly available and have professionally touched up the English language.
Thank you again for your review.
Sincerest greetings!
Yours sincerely.
Xiao Zeyan