Evaluation of Accuracy Degradation Resulting from Concept Drift in a Fake News Detection System Using Emotional Expression

Round 1

Reviewer 1 Report

I’m glad to review the paper. Then in my view, although there are some advantages, the paper should be weakly accepted, because there are some points that need to be improved:

1. All tables should be presented in three-line table.

2. Please show the comparison results in table form, the line chart does not look comprehensive.

3. Only a dataset is not enough to give sufficient proof. I hope you can continue to train the model on new data sets.

4. The content of Related Work is a bit poor, and I hope that you can add some content to make your research content more grounded.

5. As for the overall paper, the number of references is a bit small, so I suggest you continue to add some references.

 

 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Addressing concept drift in fake news detection is, in fact, a very important and promising issue, as trained systems based on prevalent language patterns of the past usually fail on actual data. The approach presented in the paper provides a sound solution to this problem.

There are minor sections in the paper that could be improved:

The presentation of the differences in concept drift is probably not necessary.

The sudden decline of the accuracy of some models in period 3 should be explained more convincingly. The same holds for the large-scale desaster events and their effect on fake news detection.

There is a misspelling in line 182: "coule" should read "could"

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

1. I don't quite understand why you need to use Glove. So, we think it would be best if you added a sentence to explain the reason for using it.

2. In the field of concept drift, the referenced articles are mostly quite old. We hope that you can once again cite several references from the last three years, in order to make your research more cutting-edge. If you cannot find suitable references, I recommend that you cite the following few references.

1）https://doi.org/10.1016/j.patcog.2022.109113

2）https://doi.org/10.1016/j.ins.2022.07.022

3）https://doi.org/10.1109/TITS.2021.3137446

Author Response

Please see the attachment.

Author Response File: Author Response.docx