Analyzing COVID-19 Protest Movements: A Multidimensional Approach Using Geo-Social Media Data
summary
Uses Twitter geo-social data to map Austrian COVID-19 protest networks by crawling from 100 seed accounts through followers, geocoding bio locations with Nominatim, and analyzing ~6 million tweets with geopandas, networkx and gensim. Builds a follower graph, runs community detection and centrality measures, computes Moran’s I (near 1 for clustering), and topic models that surface anti-public-broadcasting and Turkish-language clusters. Finds communities align with national borders, high-centrality actors are regionally concentrated, and half of bios lack usable locations; API access limits replication.
AI-written summary · about
chapters (9)
- 0:00Introduction to COVID-19 protests
- 2:11Data sources and approach
- 7:49Network analysis method
- 13:12Spatial analysis with geocoding
- 15:19Community detection in networks
- 18:49Spatial clustering insights
- 20:37Semantic analysis of tweets
- 23:06Social media research importance
- 23:47Q&A session
related talks
26mSocial Networks and Protest Participation: Evidence from 130 Million Twitter Users
16mGeostreams
41mCity attractiveness seen through Twitter
27mBeyond a Machine Learning Model
13mGeometry for Social Good
41mDemystifying Social Network Analysis (SNA)
38mAnalysing Russian Troll Tweets data with Python
24mHands-On Network Science