Overlapping Community Detection of Bipartite Networks Based on a Novel Community Density
Round 1
Reviewer 1 Report
The authors propose a novel function for Community Detection and evaluation of the bipartite network, called community density D. And a bipartite network community detection algorithm DSNE(Density Sub-community Node-pair Extraction) is proposed.
In general the writing, spelling and grammar are correct.
In contrast, I found the presentation of the quality function D difficult to understand in section 3.1, whereas this is the main contribution of the paper, the authors should make sure that this part lacks of mistakes, specially in the equations. There seems to be some mistakes in formula, for instance, in equations (9) and (10) what does the letter k represent?, in expression (8) from my understanding the sum sign means summing up all the nodes vk such that vk belongs to PN(m) or PN(m), etc. In summary I think this part deserves to be re-read and even illustrated with a simple example.
Another remark, the authors claim that the proposed function does not suffer from resolution limitation. I wonder if they are talking about resolution limit which is a well-known problem in the community detection literature that was originally highlighted by Fortunato in 2007 in his seminal paper "resolution limit in community detection". However, this paper is not even mentioned in the references.
Next, when they compared the 2 partitions in Figure 1, they claimed version (a) is better than (b). However, it is a complete bipartite graph. Logically, the best partition is the one where all the nodes are put in a single cluster. So, there are no cuts, no edges between clusters.
I did not read any further since, to understand the following the quality function definition must be clear.
Additional suggestions:
-
In the abstract "more" important => more than what? the word more is used for comparison
-
P.4 punctuation: set.Likewise,PN (v)
-
P.5 suggestion: please, add a figure to schematize NeiPN (u, v)
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
I have included my comments to the article in the attachment FI_r.docx
Comments for author File: Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
In most cases, the authors took into account my comments and added examples that improve readability of the article. However, I still believe that the article is difficult to read and a full understanding of the issues raised by the authors requires the reader to read the previous works of the authors. In addition, the entire article requires review and elimination of errors that still occur in the formulas and definitions of some parameters, for example: should formulas 4 and 5 not define the sum in a similar way ?; line 203 is an error - the parentheses are at the wrong levels; in algorithm 1, the role of the alpha and beta parameters is very briefly explained; figure 8 is basically a copy of figure 2.
Despite these drawbacks, I believe that due to the very important topic of the article, it can be published after corrections have been made.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
