Influenza related tweets in Weibo
2019-01-04T01:51:54Z (GMT) by
The dataset contains two files. In the file "ILI_data_set.csv", each line represent a recode of ILI, in which the first column is time (in week), the second column is the influenza rate in northern China and the third column is the influenza rate in southern China. In the file "weibo_tweets_data_set.csv", all the influenza related tweets identified by our classifier are contained. And in each line, one tweet's created_time, text and posted location (at the city level) are sequentially listed.
Our paper on this data set: https://arxiv.org/abs/1905.01778.
Any issue regarding the data set please contact firstname.lastname@example.org.