2

I am currently doing a sentiment analysis project about the online tweets. The tweets were collected by a previous guy in my group using R. And now I am using Python. A sample of the collected tweets is given below:

Wherever we go with it becomes a cafe!
.....
<ed><U+00A0><U+00BD><ed><U+00B3><U+00B7>: mad.maps  -  "Slow down and <url>

It seems like the <ed><U+00A0><U+00BD><ed><U+00B3><U+00B7> corresponds to the emoji after checking the original tweet. Hence, I really want to know how to transform the <ed>...<ed>... things to the correct emoji. Or how could I link the <ed><U+00A0><U+00BD><ed><U+00B3><U+00B7> stuff to 's Unicode, which is U+1F4F7?

Any help and insights would be appreciated! Thank you!

PS:

  1. The Emoji-Unicode pair I am using is given here: Full Emoji List, v11.0

  2. This pdf file also provides some emoji-emoji_code pair, but it is not enough: emoji to emoji code

Bright Chang
  • 191
  • 2
  • 14
  • Do you hapen to know how he got the ``. Maybe he knows what encoding or notation it is? – handras Dec 29 '18 at 10:08
  • [Here](https://stackoverflow.com/questions/37999896/twitter-emoji-encoding-problems-with-twitter-and-r) you go :-) – Alex Dec 29 '18 at 10:11

0 Answers0