A New Approach to Refining Land Use Types: Predicting Point-of-Interest Categories Using Weibo Check-in Data
Round 1
Reviewer 1 Report
This submission is a very interesting paper with a very applied topic and falls in the scope of the journal. Although, it has some potential for improvement.
The general description of the problem (Introduction) and the description of its importance for the science and the society could be further improved. The degree of innovativeness of the methodological approach is not convincingly demonstrated. Some more details about its innovative features could further improve the quality of this paper. Why is this paper likely to be cited in the future?
A bit more text regarding the originality of this work and why it contains new results that significantly advance the research field.
I believe that adding a bit more text on why the results of the method are satisfactory (evaluation approach) will increase the quality of this work. Could the results be more satisfactory if you have changed something in the methodology? Are the results (or the method) sensitive to this specific study area?
In the Discussion section I would have wished to see more information on the actual meaning of the findings and how the results add to the broader topic as well as the specific scientific field. The "Conclusions" section, could be further improved by describing the importance of this work, the highlight of potential further development of this methodology.
Author Response
Many thanks for your useful and helpful comments. We carefully revised the paper according to your comments. The changes we made have been marked in red colour for reviewer to find the changes quickly. It is worth mention that a few graphs are slightly modified due to our mistake of using outdated district map. We are sorry for that. We hope you are satisfied with the revised paper. Our responses to your specific comments are below.
Referee: 1
- The general description of the problem (Introduction) and the description of its importance for the science and the society could be further improved. The degree of innovativeness of the methodological approach is not convincingly demonstrated. A bit more text regarding the originality of this work and why it contains new results that significantly advance the research field.
Response:
We added some text (see the red word in Page 1, 2 and 3) to describe the importance for society, possible application, innovation and improvement.
- I believe that adding a bit more text on why the results of the method are satisfactory (evaluation approach) will increase the quality of this work.
Response:
We added several evaluation indicators to estimate the results of different methods and use a graph to visualize the results of evaluation indicators (see the red word in Page 13 and 14; and Figure 11 in Page 15).
- Could the results be more satisfactory if you have changed something in the methodology? Are the results (or the method) sensitive to this specific study area?
Response:
We examined the influence of some parameter changes (e.g., number of trees and number of splitting variables) on the results (see Figure 10 in Page 13). Through the experiment regarding the other parameters of method, we found that, in our study, changing other parameters do not have a significant influence for prediction accuracy. Therefore, we do not discuss the influence of other parameters in detail. Furthermore, we can’t test the applicability of the method to other study areas due to the lack of relevant data in other cities. We plan to test the applicability of the method other study areas in the near future once we collect all the relevant data.
- In the Discussion section I would have wished to see more information on the actual meaning of the findings and how the results add to the broader topic as well as the specific scientific field.
Response:
We added a paragraph (see the red words in Page 15) to describe the possible application of the findings to the urban plan field, as well as the part possibilities of further development.
- The "Conclusions" section, could be further improved by describing the importance of this work, the highlight of potential further development of this methodology.
Response:
We added some text (see the red word in Page 16 and 17) to describe the necessity of our work and the potential further improvement of the work.
Reviewer 2 Report
The manuscript titled “A new approach to refining land use types: predicting point-of-interest categories using Weibo check-in data” represents interesting scientific research. The idea of the study is interesting and presents enough novelty. The paper title is accurate and concise. In the entire manuscript, authors use standard technical and scientific terminology. Methodology and results were conducted according to the scientifically correct approach. The conclusions are logical and based on the results of the research. The paper topics fit in the International Journal of Geo-Information sensing aims and scope. I recommended this paper to be accepted after major revisions.
Comments for authors:
Although the manuscript topic is interesting, the real research application of the developed method must be researched and explained in detail. I suggest adding a paragraph(s) to emphasize more the applicability of the proposed method in the future. I suggest adding a paragraph(s) with an explanation of the classification methods. Also, including some state-of-the-art references for this topic will increase the quality of the research. 18th references for this kind of research article is not enough. I suggest to research and include following papers: “Random forests for land cover classification”; “Optical remotely sensed time series data for land cover classification: A review”; “Automatic cost-effective method for land cover classification (ALCC)”; “Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery”. Use MDPI standard font (Palatino Linotype) on figures if you can. Use MDPI standard font (Palatino Linotype) in the manuscript text. Add legends on figures 6 and 9. Define abbreviation if you want to use it in the manuscript text (e.g. LBSN). Remove borders on figures 3 and 8. Correct some typos in the manuscript text (e.g. “(3)the user whose” -> “(3) the user whose”; “ith”->”i-th”; “in our model shown as Table .” -> “in our model shown as Table 3.” The variable names must have the same font style and size in equations, on figures, tables, and in the manuscript text. Please describe/introduce all variables used in equations or on figures in the manuscript text. All equations must be adequately cited in the entire paper. Remove some redundant sentences in the manuscript text (e.g. first and second sentence in section 2.2) Please, double-check all references and reference style.Author Response
Many thanks for your useful and helpful comments. We carefully revised the paper according to your comments. The changes we made have been marked in red colour for reviewer to find the changes quickly. It is worth mention that a few graphs are slightly modified due to our mistake of using outdated district map. We are sorry for that. We hope you are satisfied with the revised paper. Our responses to your specific comments are below.
Referee: 2
- the real research application of the developed method must be researched and explained in detail. I suggest adding a paragraph(s) to emphasize more the applicability of the proposed method in the future.
Response:
We added a paragraph (see the red word in Page 15) to describe the possible application of the method in the future.
- I suggest adding a paragraph(s) with an explanation of the classification methods.
Response:
We added a paragraph (see the red word in Page 5 and 6) to explain our POI-level land use classification method, and visualize the workflow of the method (see the picture 4 in Page 6).
- 18th references for this kind of research article is not enough. I suggest to research and include following papers: “Random forests for land cover classification”; “Optical remotely sensed time series data for land cover classification: A review”; “Automatic cost-effective method for land cover classification (ALCC)”; “Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery”.
Response:
We added 5 references (see the red word in Page 6, 12, and 15 respectively) not only the references you recommend for increasing the quality of the paper.
- Use MDPI standard font (Palatino Linotype) on figures if you can. Use MDPI standard font (Palatino Linotype) in the manuscript text. Add legends on figures 6 and 9. Define abbreviation if you want to use it in the manuscript text (e.g. LBSN). Remove borders on figures 3 and 8. Correct some typos in the manuscript text (e.g. “(3)the user whose” -> “(3) the user whose”; “ith”->”i-th”; “in our model shown as Table .” -> “in our model shown as Table 3.” The variable names must have the same font style and size in equations, on figures, tables, and in the manuscript text. Please describe/introduce all variables used in equations or on figures in the manuscript text. Remove some redundant sentences in the manuscript text (e.g. first and second sentence in section 2.2) Please, double-check all references and reference style.
Response:
We are sorry for the negligence of the detail. We revised the mistakes already.
Round 2
Reviewer 2 Report
The authors have addressed almost all reviewers' comments, and the manuscript in its current version is improved compared to the original.
Please, use one letter instead of the entire word for the variable name (e.g. accuracy, precision, etc.).
Please, use GNSS (global navigation satellite system) abbreviation instead of GPS.
I have no further comments, and the revised manuscript can be accepted.
Author Response
Many thanks for your useful and helpful comments. We further make revisions according to your new comments. The changes we made have been marked in red colour for reviewer to find the changes quickly. We hope you are satisfied with the revised paper. Our responses to your specific comments are below.
- Please, use one letter instead of the entire word for the variable name (e.g. accuracy, precision, etc.).
Response:
We replaced the variable name and indicator name with one letter (see the red word in Page 9, 13 and 14).
- Please, use GNSS (global navigation satellite system) abbreviation instead of GPS.
Response:
We replaced the GPS with GNSS (see the red word in Page 15 and 17).
This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.
