Junction and disjunction in public opinion - Facebook users attitudes towards migrations between 2014 and 2018
Alexandre Leroux, Matteo Gagliolo
Belgium, and Europe in general, experienced an increased attention of public
opinion to immigration in the last few years, accompanied by outbursts of
activity on online social networks, ranging from solidarity with migrants and
refugees, to xeno- and Islamophobia. These digital traces provide ground to
study citizens' opinions and attitudes towards refugees and migrants. Combining
textual information with Facebook network features allows us to piece together a
topography of the disparate citizen narratives about migration. Our ongoing
research aims to investigate those opinions and their evolution, as discussed on
Facebook.
The analysed corpus consists of 24.8 million comments written on a set of 15 000
Facebook pages related to migration, between 2014 and 2018, collected via the
platform's API. Out of the 6000 pages reporting geographic data, 83\% are located
in Belgium. For this work we will focus on the comments to posts published on
French-speaking pages.
As we are interested only in migration related discourse, after lemmatizing and
filtering out stop words, we further filter the dataset through string matching,
using /word2vec/, keeping only comments containing terms with the highest
lexical and semantic similarity to ``refugees'' and ``migrants''.
In order to observe the evolution of discursive patterns over time, we follow an
approach similar to Rule, Cointet, and Bearman (2015): we split the collection
of comments in four-month intervals and define the corresponding co-occurrence
networks, where the nodes represent lemmas, and the weighted edges represent the
similarity between each pair of lemmas, evaluated as the cosine similarity among
columns of the lemma-comment matrix. We then identify themes by clustering each
network, and labeling the obtained communities of words .
In the last step of our analysis, we will look upon the relationships among
these communities, and their evolution over time. Using Bhattacharyya distance,
we intend to measure the temporal evolution of the distribution of lemmas within
each cluster, as well as define a macro temporal network connecting the themes,
and varying across the 4-months periods. This should allow us to observe the
impact of punctual events, and identify trends in the public discourse over this
5-year period.← Schedule