Polarity-Based Sentiment Analysis of Georeferenced Tweets Related to the 2022 Twitter Acquisition

Round 1

Reviewer 1 Report

Does the introduction provide sufficient background and include all relevant references?

The introduction and review of the literature provide the context and relevance of the problem. They are clear and show the timeliness and value of the proposed topic.

 

Are all the cited references relevant to the research?

 From an interdisciplinary approach, the references are relevant for both the actuality of the topic and its methodological contributions, as well as for future studies that transcend the topic covered by the authors. Beyond the academic sphere, studies on the expression of sentiment in social networks are also of interest to studies related to marketing from an industry perspective and the impact of their products on societies. The findings of this study are relevant to other contexts.

 

Is the research design appropriate?

 The design is very appropriate, and it emphasizes the clear organization of the article positively. Three aspects stand out: 1) How the data were obtained; 2) the processes followed in the analysis of sentment; 3) analyses related to geographical location.  

 

Are the methods adequately described?

Further clarification is recommended due to the complexity and novelty of the data collection processes.

3.1 Data

Because the article may be of interest to researchers related to social science, and not only to data scientists, some concepts could be expanded, especially by offering links that approximate the tools used.

It is not clear what has been applied by the authors, it might be useful to include a link in a footnote referring to the tool used, for example, "the Streaming and Resting API" is mentioned.

It could be specified what "PostgreSQL/PostGIS database" consists of and why they are chosen in this study.

3.2 Sentiment analysis

The way in which the analysis has been carried out could be presented more clearly, through some concrete example, or by providing links that exemplify the techniques used.

 

Are the results clearly presented?

The results of this study are clearly presented, and the conclusions are based on them.

 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

It may be worth noting in the introduction the major reason behind Musk's desire to purchase Twitter ("freedom of speech," he felt conservative voices were being silenced, etc.). Additionally, it may be worth noting that hate speech and the use of racial slurs increased significantly after he acquired Twitter.

I think you did a great job describing how you collected your Tweets.

Word clouds are great for presentations, but for an academic paper I would prefer to see a table with the actual frequencies of the top words. If you chose to keep the word cloud, I believe you should at least provide the frequencies in the paragraphs of each of the most frequent words. With that, I do not see in your discussion where you discuss word frequency and sentiment combined. I think it is interesting to combine these two analysis, but you don't do much with them other than the word cloud it seems.

In the discussion, you say that you assume that negative tweets increased due to employee termination, but I think there was more than just that going on. Employees being laid off was a big part of it, but there were many other things that people were unhappy with during this time.

Line 127 - the word 'by' seems unnecessary.

Line 184 - not sure why you use the word chapter.

Author Response

Please see the attachment

Author Response File: Author Response.pdf