How workforce migrates in China: A perspective from social media

Weibo Data Description:<br>Tweets of Weibo during the Spring Festival travel rush, from January 13 to February 21 in 2017 are thoroughly collected to establish the migration network of workforce at the granularity of city.<br>Basic Statistics:<br>Number of cities: 371Number of city pairs(directed): 120,361Number of city pairs(undirected): 61,759Number of all flux: 41,454,268 <br>Data Format:<br>Each line in the file(WorkforceMigrate.csv) demonstrates a 12-tuple (city1,city2,flux,gdp1,gdp2,ave_gdp1,ave_gdp2,population1,population2,geographical_distance,travel_time,travel_distance) defined to denote workforce movement from city1 to city2. Details can be found as follows.<br>1. city1: origin city id2. city2: destination city id3. flux: number of movements from city1 to city24. gdp1: GDP of city15. gdp2: GDP of city26. avg_gdp1: the per capita GDP of city17. avg_gdp2: the per capita GDP of city28. population1: the number of permanent residents in city19. population2: the number of permanent residents in city210. geographical_distance: geographical distance between city1 and city211. travel_distance: travel distance from city1 to city2 provided by Baidu Map API12. travel_time: travel time from city1 to city2 provided by Baidu Map API<br>Data Description:<br>The demographic and economic information in 2015 are collected at the granularity of province.<br><br>Province Data Format:<br>Each line in file(ProvinceInfo.csv) demonstrates a 8-tuple (province, gdp15, Information Technology Industry,Financial Industry,Real Estate Industry,Scientific Research and Technical Services Industry,income15,R&amp;D) defined to denote the economci information of provinces. Details can be found as follows:<br>1. province: province id2. gdp15: GDP of province3. Information Technology Industry: ratio of practitioner in the information technology industry4. Financial Industry: ratio of practitioner in the Financial industry5. Real Estate Industry: ratio of practitioner in the real estate industry 6. Scientific Research and Technical Services Industry: ratio of practitioner in the scientific research and technical services industry 7. income15: per capita disposable income8. R&amp;D: the fund investment for research and development<br>Train Data Desciption:<br>The national railway line data, including 5,878 trains in total from train schedule are collected to establish the train network at the granularity of city.<br>Basic Statistics:<br>Number of cities: 284 citiesNumber of citi pairs(undirected): 12381<br>Data Format:Each line in the file(Train.csv) demonstrate a triple (city1, city2, train_count) defined to denote trains that pass through city1 and city2. Details can be found as follows:<br>1. city1: city id2. city2: city id3. train_count: the number of trains that pass through city1 and city2<br>Any issues please feel free to contact [e-mail].