Comments are off for this post

Using AI for Multi-Country Automated Protest Event Collection

Emerging Welfare Project team — Assoc. Prof. Erdem Yoruk, Dr. Ali Hurriyetoglu, Dr. Cagri Yoltar, and Firat Durusan– will be presenting at GLODEM AI & CSS Seminar Series on December 3, 2020 at 06:00-07:30 PM(GMT+3).

This seminar will speak about the potentials and challenges of using AI to understand social movements and present the new bottom-up methodological approach that has been adopted by the GLOCON Project. It will be shown that creating a gold standard corpus for training and testing machine learning models on the basis of randomly chosen news articles from news archives yields better performance than selecting news articles on the basis of keyword filtering, which is the most prevalent method currently used in automated event coding. The results of comparing the random-sample approach to keyword filtering will be presented, and it will be illustrated that the machine learning algorithms, and particularly state-of-the-art deep learning tools, perform much better when they are trained with the gold standard corpus from a randomly selected set of news articles from China, India and South Africa.

Please visit to register for the event (advance registration required).


The full video of the seminar can be found here.

Comments are closed.