Create algorithm
Opened this issue · 2 comments
MichielOHerne commented
-
- Write code to acces the saved twitter data and load all variables
- - open data files containing tweet information
- - download/import pre-made datasets including only geotagged tweets
- - sort into datasets, grouped by subject:
- - pizza: all tweets containing "pizza", "pizzeria", "#pizza" and such
-
- data sets to create:
- -
- -
- -
- -
-
- write code do sentiment analysis on the datasets
- - positive / negative
- - overall opinion
- - popularity
- - location based
-
- write code to store sorted data
- -
- -
- -
MichielOHerne commented
pynltk
MichielOHerne commented
476 million tweets data set - 1june-31dec 2009
http://snap.stanford.edu/data/bigdata/twitter7/tweets2009-06.txt.gz
http://snap.stanford.edu/data/bigdata/twitter7/tweets2009-07.txt.gz
http://snap.stanford.edu/data/bigdata/twitter7/tweets2009-08.txt.gz
http://snap.stanford.edu/data/bigdata/twitter7/tweets2009-09.txt.gz
http://snap.stanford.edu/data/bigdata/twitter7/tweets2009-10.txt.gz
http://snap.stanford.edu/data/bigdata/twitter7/tweets2009-11.txt.gz
http://snap.stanford.edu/data/bigdata/twitter7/tweets2009-12.txt.gz