A Computational Framework for Multi-Modal Social Action Identification
This provides a diagnostic tool for researchers, government officials, and the public to analyze peaceful and violent collective action at detailed temporal and geographic scales, though it is incremental as it applies existing methods to new data.
The authors tackled the problem of understanding social action by developing a computational framework and an open-source event detection tool using scalable machine learning algorithms on a database of over 600 million geo-tagged Tweets, enabling fine-grained analysis of collective actions like the Black Lives Matter movement.
We create a computational framework for understanding social action and demonstrate how this framework can be used to build an open-source event detection tool with scalable statistical machine learning algorithms and a subsampled database of over 600 million geo-tagged Tweets from around the world. These Tweets were collected between April 1st, 2014 and April 30th, 2015, most notably when the Black Lives Matter movement began. We demonstrate how these methods can be used diagnostically-by researchers, government officials and the public-to understand peaceful and violent collective action at very fine-grained levels of time and geography.