Random vs. expert sampling of tweet streams
Several research studies / applications today rely upon content streams crowd-sourced from online social networks.
Since real-time processing of large amounts of data generated on these sites is difficult,
analytics companies and researchers are increasingly resorting to sampling.
In this project, we investigated the crucial question of how to sample the
data generated by users in social networks?.
The traditional method is to randomly sample all the data, e.g.,
most researchers / applications today rely on the 1% and 10% randomly sampled streams
of tweets provided by Twitter.
We proposed and analyzed a different sampling methodology, where content is gathered only
from a relatively small set of expert users. Over the duration of a month, we gathered tweets from over 500,000 experts on a
diverse set of topics, and compared the resulting expert-sampled
tweets with the 1% randomly sampled tweets provided publicly by Twitter on a variety of aspects --
the diversity, timeliness, and trustworthiness of the information contained in the tweet-samples.
Our observations revealed significant differences in data obtained through the different sampling methodologies, which has
major implications for applications such as topical search, trustworthy content
recommendations, and breaking news detection.