The Datagotchi app, which has been accessible online since Tuesday morning, was designed by the research team in the Leadership in Digital Social Science Teaching at Université Laval (CLESSN).
After comparing the effectiveness of different statistical models, the designers of the web platform, whose name is a nod to Tamagotchi, that virtual pet who was all the rage in the 1990s, trained a learning algorithm capable of predicting users’ voting intentions from a list of 30 questions.
These range from sexual preferences to the means of transportation most used, hair length, type of dwelling, and level of interest in hunting and outdoor sports. A user avatar is formed when a survey is completed.
If the app uses classic sociodemographic characteristics such as age, gender, and place of residence, it focuses first and foremost on the user’s lifestyle, insists Catherine Oleh, PhD candidate. in Political Science at the University of Toronto and collaborating on the project.
This is to show, roughly, that these variables, where we stand, what we do, what we eat, etc., can tell us more about who we are and what we think and can be particularly rich, when we are interested in politics, then they can also be variables he will use StrategistsShe explains in an interview with the program all morning.
The researcher specifies that there is no direct relationship between a voter’s preferences, for example, and their taste for a latte. Lifestyle habits are treated in the same way as traditional sociodemographic variables, whose predictive power tends to be low.
It’s not the fact that I drink a latte that makes me vote, say, conservative. It’s not watching this kind of movie that makes me vote for the Greens, it’s an indication of something elseMrs. Owlette insists.
These are signs [ou] Socialization units that can allow us to identify new groups of voters.
In this digital age, where every transaction is made on Amazon and every hour is made on Netflix
leave tracesThe researcher believes that it is important for voters to understand that their lifestyles can be restored for political ends.
We really try to educate citizens about the wealth of this data and then the information they can provide about us, without always necessarily realizing it.Catherine Ole insists.
Like other members of the team behind creating Datagotchi, she hopes the app will enter the norms of Quebec voters and Canadians, just like the electoral compass, which CLESSNhave also contributed.
To access the Datagotchi platform, Click on this link (A new window).
“Total creator. Evil zombie fan. Food evangelist. Alcohol practitioner. Web aficionado. Passionate beer advocate.”