in 
, via 
| she/her
https://twitter.com/azpoliak/status/1144094774296809472 … Why not measure "speak time" based on the actual number of seconds a candidate spoke for? One issue I can think of is what happens when one candidate talks over another - does that time count for both candidates (same q applies to word counts too)?
Speaking time in the first debate was correlated with candidates’ polling averages (R=0.55), though some candidates (like Booker and Castro) spoke a lot relative to how they're doing in the polls, while Warren got fewer words in than her standing would imply.pic.twitter.com/tXtwwGGaxM
-
-
-
You're right, it's a proxy -- we have easy access to the transcript but didn't time speakers. :) And as you say, crosstalk is an issue regardless of whether you use words or time. The transcript is good at distinguishing them, but when it's unintelligible it doesn't get counted.
- 2 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.