Online Social Network Information Source Identification Algorithm Based on Multi-Attribute Topological Clustering

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

In this paper, the authors address the challenge of identifying original information sources within online social networks (OSN). They explore the complexities of information spread and network structures, introducing a novel algorithm called multi-attribute topological clustering (MaTC) designed to enhance the accuracy and efficiency of source detection. The MaTC algorithm approaches the issue by breaking down multi-source scenarios into simpler single-source cases using a clustering method. This method not only estimates the number of source nodes but also employs a multi-attribute framework for more precise topological clustering.

The paper focuses on a well known and interesting context. The methods are described soundly and the experimental evaluation seems appropriate. Nevertheless, the paper exhibits some drawbacks that actually undermine its quality. In light of this, I suggest the authors to revise the paper taking into account the following comments:

• The related work investigation is well conducted. Nevertheless, the presentation lacks some details. First off, starting from the previous works, I suggest introducing a table to summarize the most recent works and to highlight the novelty of the proposed work w.r.t the literature. Also, information diffusers have been extensively studied in the literature. I suggest the authors to consider recent references such as [10.1016/j.datak.2022.102048] and discuss them.
• How the proposed model compare with diffusion processes? If I recall correctly, the likelihood estimation in Equation 1 could be approximated via a diffusion process. In this case, how would it benefit the current approach?
• What is a case study in which the current approach could be useful? This question arises from the fact that while the methods are described soundly and the experimental evaluation is solid, the implications are not very clear. I suggest the authors to provide a discussion about the theoretical and practical implications of such work.
• The paper lacks clear information on the specific modifications or improvements proposed over existing work. Indeed, the literature presents a plethora of works on information source identification, which is commonly called with nomenclatures such as key players identification, influential nodes identification, and so on. Therefore, the authors should provide an experimental comparison with at least one selected method from the literature.
• What are the limitations of this approach? For example, could be used in large networks?
• Figure 1 could be more organized. Provide more information about the workflow.
• Finally, there are some typos and unusual sentences construction. I suggest the authors to carefully read the paper and fix those.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This paper focused on the problem of information source identification in an online social network and proposed MaTC to study the problem of multiple source diffusion. Finally, the algorithm achieved a good result in evaluating indicators. However, there are some problems that must be solved before it is considered for publication.

1. The figures in the paper are blurry. Please consider replacing them with clearer ones.

2. The steps of the algorithm would be clearer if they were expressed in Pseudocode (lines 399-415).

3. Explain why the MaTC identification algorithm performs better than other algorithms.

4. Keywords should be lowercase.

5. The first paragraph of section 2 needs to be deleted. The text on the template does not seem to be commented out.

6. There are some problems with citing references. For example, in line 88, it should be “Luo et al.”; in line 143, it should be “Louni and Subbalakshmi” or “Louni et al.” Please check carefully when citing references.

Comments on the Quality of English Language

The manuscript has at least two grammatical mistakes. For example, in line 311, add “if” before “your neighbor”; in line 581, “it” would be “It.” Please check the manuscript carefully.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

In this paper, the authors proposed an source identification algorithm based on multi-attribute topological clustering. Although the topics seem interesting, the authors should address the following issues:

1. In Chapter 1, the broad context  and research gap are not clear. Please highlight the list of contributions.

2. In the literature review section, many old papers were cited, could you cite some more recently published papers? Furthermore, please highlight the differences of your approach with recent works in the literature.

3. In the literature review section, please remove first paragraph “The Materials and Methods should be described with sufficient details...".

4. In section 4.2, you describes BC, CC, DC, SJC algorithms. Please provide some references and explain the reason for their choice. Alternatively, could you validate your proposal with an approach found in the literature (even an approach cited by you)?

5. In Experimental Results and Analysis, the number of source nodes on the data sets is obtained. It would be interesting to show a table with more information on some of these source nodes.

6. The algorithm identifies the single source for each partition. It is unclear how to utilize results obtained in this paper, could the authors improve this?

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors successfully addressed my raised concerns. I do not have any more comments on the paper.

Reviewer 3 Report

Comments and Suggestions for Authors

Good to see your revised draft. The paper is now suitable for publication. Congratulations.