Thread by @timothyjgraham

Just to clarify, the primary interest here is Twitter's design features and dynamics, and how a single account (@PRGuy17) managed to get a hashtag to #1 on the Australia trending list in less than 1 hour

(1/5)

https://twitter.com/PRGuy17/status/1345991148318257153

I ran sentiment analysis to provide a quick comparison with our peer-reviewed study of hashtag publics during #Covid19Vic, where we found that pro-Andrews tweeters were overwhelmingly positive and anti-Andrews tweeters were overwhelmingly negative:

journals.sagepub.com/doi/full/10.11…

(2/5)

But I agree with criticism of VADER and similar tools, especially limitations for detecting irony and sarcasm. Folks are right to question it

And we acknowledge its limitations in the paper above and highlight its usefulness at scale as part of a broader suite of methods

(3/5)

To sum up:

Sentiment analysis is a side show to the real issue, which is how easily and quickly Twitter's trending list can be gamed -- in this case, by an anonymous account with 14.5k followers that tweets all day every 20 minutes

(4/5)

Finally, if you're interested to learn more please check out our latest article in @ConversationEDU

We squarely point blame at partisan mainstream media and do a 'deep dive' into the dynamics and drivers of hashtag campaigns

(5/5)

theconversation.com/istandwithdan-…