search

researchart / swan17

0 stars 0 forks source link

bamzii: Social Media Analytics: Twitter Users Responses to Financial Events #3

Open timm opened 7 years ago

timm commented 7 years ago

(NOTE: authors have waived the blinded option for their names)

Social Media Analytics: Twitter Users Responses to Financial Events

https://github.com/researchart/swan17/blob/master/pdf/bamzii.pdf

Twitter data can be used to study social response to political and economical events and major political or economical leader’s decisions. we have analyzed tweets and their relationship to relevant news events, press releases, and important political or banking individuals. We have shown how machine learning methods can be used to extract social emotional responses. using the natural language processing algorithms, Naive Bayes Classifier and opinion lexicon we have studied tweets structures and by Using visualization and sentiment analysis, we’ve found how people has responded towards the heads of the central banks.

GENERAL TERMS

Social Media, Sentiment Analysis, Central Banking, text analysis

timm commented 7 years ago

AUTHORS: Important. Do NOT reply till all three reviews are here (until then, we will delete your comments)_.

Reviewer1

Insert reviewer github id here ==>

Recommendation (select one)

Summary (1 para)

The paper analyzes tweets related to central banking. Some descriptive statistics (most frequent terms, most retweeted accounts) are collected, news events are mapped for a specific central bank, and sentiment analysis is applied.

Advocacy (accept since, reject since, 1 para)

Although the paper presents on an interesting project, I fail to see how it is relevant to this workshop. The topic is only related to software in that software is used to collect and analyze the data. No discussion is offered regarding how the techniques used or lessons learned might be applied to software analytics.

List of "Pros"

List of "Cons"

Changes needed before I can recommend accept (if any)

timm commented 7 years ago

_AUTHORS: Important. Do NOT reply till all three reviews are here (until then, we will delete your comments)_.

Reviewer2

Insert reviewer github id here ==>

Recommendation (select one)

Summary (1 para)

This is a paper about how to use machine learning methods on tweets to discern Twitter users' responses to financial concepts.

Advocacy (accept since, reject since, 1 para)

This paper is not relevant to the conference. The authors may have confused "using software for analytics" for "software analytics".

List of "Pros"

Interesting paper.

List of "Cons"

Not relevant to this conference/workshop.

Changes needed before I can recommend accept (if any)

timm commented 7 years ago

_AUTHORS: Important. Do NOT reply till all three reviews are here (until then, we will delete your comments)_.

Reviewer3

Insert reviewer github id here ==>

Recommendation (select one)

Summary (1 para)

This paper presents a sentimental analysis on tweets. It uses some basic machine learning tools to classify the emotional response of tweets.

Advocacy (accept since, reject since, 1 para)

This paper does not relate to software analytics, even at a stretch. If the sentimental analysis were done on this like bug reports, documentation, etc., this could be interesting to this workshop. However, as it stands, it does not relate to this workshop. Further, there is related work for software analytics on sentimental analysis that is uncited. As such, this paper is irrelevant to this workshop.

List of "Pros"

List of "Cons"

Changes needed before I can recommend accept (if any)

timm commented 7 years ago

the authors clearly demonstrate their technical competence in this area.

but I'm having two issues with this paper:

note that a good answer to the second point might also address the first point.

authors? discuss?