Developing the NLP-QFD Model to Discover Key Success Factors of Short Videos on Social Media

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The paper proposes a method that uses Natural Language Processing (NLP), Latent Dirichlet Allocation (LDA), and Quality Function Deployment to determine what factors need to be considered during production to increase viewership.

The manuscript needs to be improved, especially consider the following points:

+ In the last para of the "Introduction" section, the authors summarize what they have done, however, it has not come out clearly what the contributions are. What are the new findings? Why LDA & QFD have been used? Is it the first time the authors are using these techniques for the analysis at hand and why?

It would be better if the authors could summarize their contribution in a few bullet points.

+ Section 2 lacks critical examinations on works done in the past on the related topic. For example, in Section 2.2, the authors describe works that tried to find movie success factors, but they just describe what they did in a line or two, and did not do any critical examination of those works. What are the drawbacks of those works? How useful or successful they were in identifying the success factors? Section 2 needs to have a critical discussion of current works.

+ The "Methodology" section is very poorly written and hard to follow. I would suggest drawing a flowchart or writing an algorithm depicting the whole process.

+ Summarize the key findings in the study, specially in relation to the key success factors of a short video.

 

 

 

Comments on the Quality of English Language

English needs to be improved.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This paper introduces the NLP-QFD model to identify success factors for short videos on social media. The organization is clear, and the authors employ a systematic approach. However, there are areas that could benefit from improvement:

 

- In abstract, it is crucial to demonstrate the effectiveness of the proposal by summarizing the experimental results.

- The use of just two case studies, mainstream Western media CNN and regional media Middle East Eye, is inadequate to fully establish the efficacy of the proposed NLP-QFD. A more comprehensive structural analysis requires short videos covering a wider range of topics from various platforms.

- The limited number of topics discussed in Figures 3, 6, Tables 1, and 2 raises the question of whether these are sufficient to demonstrate the superiority of your approach. If these topics are of specific interest, it would be prudent to declare them as the main focus of the analysis in this paper. Additionally, an analysis of these topics’ characteristics and a policy for topic selection should be provided.

- The text in Figures 4 and 5 is too small to read easily. Enhancing the legibility of these figures is necessary.

 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The quality of the paper of the paper has improved, however, the following issues persist:

1. For some strange reason, the quality of the figures has decreased. Some of the figures which were ok in the previous submission have deteriorated in the revised version. It may be that the authors have scaled the figures. The figure quality needs to be improved.

2. At the end of the "Introduction" section, add a paragraph describing the structure of the paper. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf