Effects of Sampling on Twitter Trend Detection

Andrew Yates, Alek Kolcz, Nazli Goharian, Ophir Frieder


Abstract
Much research has focused on detecting trends on Twitter, including health-related trends such as mentions of Influenza-like illnesses or their symptoms. The majority of this research has been conducted using Twitter’s public feed, which includes only about 1% of all public tweets. It is unclear if, when, and how using Twitter’s 1% feed has affected the evaluation of trend detection methods. In this work we use a larger feed to investigate the effects of sampling on Twitter trend detection. We focus on using health-related trends to estimate the prevalence of Influenza-like illnesses based on tweets. We use ground truth obtained from the CDC and Google Flu Trends to explore how the prevalence estimates degrade when moving from a 100% to a 1% sample. We find that using the 1% sample is unlikely to substantially harm ILI estimates made at the national level, but can cause poor performance when estimates are made at the city level.
Anthology ID:
L16-1479
Volume:
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
Month:
May
Year:
2016
Address:
Portorož, Slovenia
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
2998–3005
Language:
URL:
https://aclanthology.org/L16-1479
DOI:
Bibkey:
Cite (ACL):
Andrew Yates, Alek Kolcz, Nazli Goharian, and Ophir Frieder. 2016. Effects of Sampling on Twitter Trend Detection. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2998–3005, Portorož, Slovenia. European Language Resources Association (ELRA).
Cite (Informal):
Effects of Sampling on Twitter Trend Detection (Yates et al., LREC 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/L16-1479.pdf