Good article in German about Cambridge Analytics and their impact on recent elections: https://www.dasmagazin.ch/2016/12/03/ich-habe-nur-gezeigt-dass-es-die-bombe-gibt/ …
-
-
Replying to @halvarflake
actually, part of what is interesting about them is that
@zeynep proposed solutions against their strategies in 2012.2 replies 1 retweet 2 likes -
interested in learning more about that. do you have a link?
1 reply 0 retweets 1 like -
I don't really see solutions being proposed here, tbh: http://www.nytimes.com/2012/11/17/opinion/beware-the-big-data-campaign.html …
3 replies 0 retweets 0 likes -
A good research topic would be, where did "big data"/ML fail in 2016 campaign, if it really did?
1 reply 0 retweets 2 likes -
Replying to @sergeybratus @esizkur and
I believe all the models failed in the sense of not conveying the uncertainty correctly.
1 reply 0 retweets 0 likes -
Replying to @zeynep @sergeybratus and
If you read footnotes to 538, you went, ay, ay, ay. If you looked at topline, faux certainty.
1 reply 0 retweets 1 like -
Replying to @zeynep @sergeybratus and
People already statistically illiterate even about, say, margin of error, let alone modeling.
2 replies 0 retweets 0 likes -
Well, I did ML statistical learning, so I took 538 stats as I believe they meant them, "very close".
1 reply 0 retweets 0 likes
Models weren't wrong per se—but basic stuff like "errors are correlated" weren't communicated.
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.