This paper addresses the important question of how using Twitter's limited streaming API biases results in comparison to Firehose access. Surprisingly they find that for geo-tagged tweets the same amount of tweets is returned for limited bounding boxes.
References
Bookmarks
deleting review
Please log in to take part in the discussion (add own reviews or comments).
Cite this publication
More citation styles
- please select -
%0 Conference Paper
%1 morstatter2013sample
%A Morstatter, Fred
%A Pfeffer, Jürgen
%A Liu, Huan
%A Carley, Kathleen M
%B ICWSM
%D 2013
%K
%T Is the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose.
@inproceedings{morstatter2013sample,
added-at = {2014-09-19T03:01:11.000+0200},
author = {Morstatter, Fred and Pfeffer, J{\"u}rgen and Liu, Huan and Carley, Kathleen M},
biburl = {https://www.bibsonomy.org/bibtex/20ca1ee09dc203c40dc1a68802a91d9b5/becker},
booktitle = {ICWSM},
interhash = {bca742d25a5f5fa43c8f106460449b5b},
intrahash = {0ca1ee09dc203c40dc1a68802a91d9b5},
keywords = {},
timestamp = {2014-09-19T03:01:11.000+0200},
title = {Is the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose.},
year = 2013
}