Machine learning

Deciphering the Decline: A Computational Analysis of Two Decades of Canadian Newspaper Op-Eds on Freedom of Information

Newspaper op-eds are an underexplored mode of communication that frame social, cultural, and political issues. This article uses an unsupervised machine-learning approach called structural topic modelling to map changes in the content of a corpus of …

Annotating Training Data in R

Some collaborators and I recently started a project analyzing a large amount of tweets we obtained via the Twitter API. To analyze these data, we are planning to train a machine learning model, which means we need training data, which means we need annotations (‘ground truth’ as its commonly referred to in computer science).