Sidebar

This is the companion website of the article “Refugee Crisis in Europe: A Mapping of Global Conversations on Twitter”.

Citation

Cite as follow:

Stojkov Aleksandar and Warin Thierry (2021). “Refugee Crisis in Europe: A Mapping of Global Conversations on Twitter” submitted

Context

This Refugee Crisis in Europe dashboard provides an overview of the conversation dynamics on Twitter about the Refugee Crisis in Europe. We use a Natural Language Processing (NLP) approach including a Structural Topic Modeling (STM) approach to analyze the refugee crisis-related tweets.

This dashboard analyzes tweets by geography, anomaly periods and languages.

Data

We collected tweets and their metadata (latitude, longitude, retweets, hastags, etc.) over three years. The database contains 482,869 messages from September 9, 2012 to December 16, 2015.

Structural Topic Modeling

The next stage is to know which topics triggered the conversations and which ones entertained the conversations. To analyze the topics, we use the Strutural Topic Mdeling (STM) technique. The STM technique provides tools for reading text corpora thanks to algorithms. Based on the tradition of probabilistic topic models such as the Latent Dirichlet Allocation (LDA), the Correlated Topic Model (CTM), and other topic models that have been extended, the Structural Topic Model’s primary innovation is the ability to incorporate arbitrary metadata, defined as information about each document, into the topic model. Topic models enable the summarization of unstructured text, the discovery of clusters (hidden topics), and the assignment of a probability of belonging to a specific topic to each observation or document. STM has grown in popularity in recent years. The Structural Topic Model approach enables researchers to discover and estimate the relationships between topics and document metadata. We are utilising the stm package.