Concept Lattice Method for Spatial Association Discovery in the Urban Service Industry

Round 1

Reviewer 1 Report

it can be accepted now. I have no more comments on the paper.

Reviewer 2 Report

All my major concerns have been addressed.

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.

Round 1

Reviewer 1 Report

The critical aspects of the study raised in previous review have not been addressed still. Just by saying 'this study has not been done before so we are reporting this....' is not enough in my point of view. The vital points of how the study performs in time and scale has to be demonstrated quantitatively, as raised in previous review. English has to be improved a lot, as also raised in previous review. Points from previous review such as addition of flowchart, methodology diagram, overall algorithm sequence, are missing and these should be present in the paper. Plus, the paper looks haphazard and hastily put together. It needs more structuring and presently it is quite difficult to follow. With these points in mind, I recommend the paper presently is not in a publication shape.    

Reviewer 2 Report

Although authors add a brief explanation about comparison in discussion, it is not enough to emphasize the novelty of the proposed method. I do not think results and discussion have been improved enough. Then, I’ve expected a considerable enhancement in related works, however authors put only two references. So lacks in geospatial aspect still remain.
As the reply, authors state that “We think etc is more accurate.” I mean that etc must be used with dot. In the previous version, dot was missing at the end of “etc”.

Reviewer 3 Report

This paper discusses the application of concept lattice theory to spatial association mining within the context of urban service industry.

This is not a novelty in itself. Concept lattices have been used in association rule discovery in the spatial domain before: several other researchers have followed this approach as referenced in this paper. The authors mention that this approach has not been applied to the context of urban service industry and this is the focus of their research.

I have several questions and comments regarding this paper:

-What do you mean by urban services? Typically they include transportation, housing, etc. however in your paper urban services seem to primarily focus on the retail/hospitality industry. This should be clarified better from the beginning.

-I am not convinced about the novelty of your approach. As mentioned above and in your paper, concept lattices have been used by others for association rule discovery. Applying it to a specific case study (the urban services industry) in itself does not constitute scientific novelty. You need to better explain what you do differently/better than others (maybe also by comparing results obtained by others).

-In your evaluation you include a link to data you collected. However, when clicking on the link you are prompted to a webpage in Chinese. This limits access to this information to Chinese speaking researchers and therefore the replicability of your experiments.

-The most interesting aspect of the work you are proposing would be rule generation. However, this is not possible in your system at the moment (from my understanding).

-One of the major problems with this paper is readability, in part due to the lack of clarity and in part due to the improper use of the English language. The paper needs a major re-writing.

-Your discussion and conclusions need to be expanded in particular by including a critical analysis of the limitations of your approach.

 

Reviewer 4 Report

The authors present thoroughly the related work. They clearly present the background and their methodology. In addition the present clearly their application and experimental set up. Their conclusios are supported by their results.