Leveraging Machine Learning and Semi-Structured Information to Identify Political Views from Social Media Posts

Round 1

Reviewer 1 Report

With an important topic, the paper is a valuable research on the performance generated by various implementations of the Naïve Bayes classifier, combined with a semi-structured information approach, to identify the political orientation of Twitter users, based on their posts. 

The paper has a good presentation of related work, based on actual references.

The methodology, algorithms, and results are very clear.

The authors are kindly invited to specify the source of the database used in the study (line 59), to verify the clarity of the figures, and to correct some minor language errors (such as user instead of users in line 13).

Also, to comment on future developments and applications, on the possibility to use the research results for some practical usages, such as:

- studying users’ political orientation in time, as a result of following and the interactions with politicians (using @user) 

- analysing the fake news promoted by politicians and how the public is influenced 

- detecting bots specialized in spreading (fake) political views.

Author Response

We really appreciate all insightful comments and useful suggestions, which definitely will help us improve the quality and readability of our manuscript. All the suggestions and criticism are fully appreciated. All the comments are highly constructive and useful to restructure our manuscript. The manuscript has been revised according to the comments. We hope all the modifications will fulfill the requirement to make the manuscript acceptable for publication in this journal.

Author Response File: Author Response.docx

Reviewer 2 Report

Dear Authors,

After reviewing your manuscript I found it interesting and well-written. However, minor to moderate revision is recommended. Please see the attached word document for details.

Kind regards,

Reviewer

Comments for author File: Comments.doc

Author Response

We really appreciate all insightful comments and useful suggestions, which definitely will help us improve the quality and readability of our manuscript. All the suggestions and criticism are fully appreciated. All the comments are highly constructive and useful to restructure our manuscript. The manuscript has been revised according to the comments. We hope all the modifications will fulfill the requirement to make the manuscript acceptable for publication in this journal.

Author Response File: Author Response.docx