Immigration and Integration discourses in the Canadian Provinces of Quebec and Ontario from 1988-2022: An Analysis of Topics, Sentiments and Trends in Newspaper Text.

Yao Robert Djogbenou, Département de Démographie, Université de Montréal
Vissého Adjiwanou, Université Du Québec à Montréal
Solène Lardoux, Université de Montréal

This study analyzes media discourse on immigration in Quebec and Ontario from 1988 to 2022. Based on 30926 articles, 19159 from newspapers in Ontario, and 11767 from newspapers in Quebec, this study proposes an unsupervised machine learning framework to explore topics and associated sentiments over time. Using structural topic modeling, we identified 20 prominent topics in each province. We apply sentiment analysis to calculate sentiment scores associated with the topics. We then use longitudinal models to link local contextual factors, such as changes in the unemployment rate and the proportion of immigrants, to the topics and sentiments. The results suggest that the topics discussed in each province about immigration are strongly related to the economy, diversity and culture, Quebec’s independence, security, governance and politics, social services, and humanitarian aid. At the same time, sentiments on different topics suggest a more negative view of immigration and integration in Quebec than in Ontario over the study period.