Immigration and Integration Discourses in Newspapers in Ontario and Quebec from 1988 to 2022: An Analysis of Topics Trends and Associated Factors

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

This study examines the evolution of topics and tone of media content on immigration and integration in Quebec and Ontario from 1988 to 2022 and assesses the power of contextual factors on these topics. Using a dataset of 30926 full-text articles from Anglophone newspapers in Ontario and Francophone newspapers in Quebec, this article uses an unsupervised machine learning framework to examine evolved topics and associated tone. Employing structural topic modeling, we identified 20 prominent topics. We applied sentiment analysis to compute tone scores. Employing longitudinal models, we explored the effect of the proportion of immigrants, unemployment rate, and political party on the topics and tone. Findings indicate that the discourse on immigration in each province is related to the economy, diversity and culture, Quebec’s independence, linguistics issues, security, governance and politics, social services, and refugees’ resettlement. While certain topics displayed consistency over time, others have remained stable in both provinces over time. Concurrently, the tone associated with these topics suggest a more pessimistic portrayal of immigration and integration in Quebec compared to Ontario. One particularly significant discovery is the power of the proportion of immigrants, unemployment rate, political party, and the evolution of topics and associated tone within each province.

Keywords: Big data, Computational social science methods, Migrant Populations and Refugees, International Migration

See extended abstract.