Parsimonious data: How a single Facebook like predicts voting behavior in multiparty systems
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Parsimonious data : How a single Facebook like predicts voting behavior in multiparty systems. / Kristensen, Jakob Baek; Albrechtsen, Thomas; Dahl-Nielsen, Emil; Jensen, Michael; Skovrind, Magnus; Bornakke, Tobias.
I: PLOS ONE, Bind 12, Nr. 9, e0184562, 20.09.2017.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Parsimonious data
T2 - How a single Facebook like predicts voting behavior in multiparty systems
AU - Kristensen, Jakob Baek
AU - Albrechtsen, Thomas
AU - Dahl-Nielsen, Emil
AU - Jensen, Michael
AU - Skovrind, Magnus
AU - Bornakke, Tobias
PY - 2017/9/20
Y1 - 2017/9/20
N2 - This study shows how liking politicians’ public Facebook posts can be used as an accurate measure for predicting present-day voter intention in a multiparty system. We highlight that a few, but selective digital traces produce prediction accuracies that are on par or even greater than most current approaches based upon bigger and broader datasets. Combining the online and offline, we connect a subsample of surveyed respondents to their public Facebook activity and apply machine learning classifiers to explore the link between their political liking behaviour and actual voting intention. Through this work, we show that even a single selective Facebook like can reveal as much about political voter intention as hundreds of heterogeneous likes. Further, by including the entire political like history of the respondents, our model reaches prediction accuracies above previous multiparty studies (60–70%).The main contribution of this paper is to show how public like-activity on Facebook allows political profiling of individual users in a multiparty system with accuracies above previous studies. Beside increased accuracies, the paper shows how such parsimonious measures allows us to generalize our findings to the entire population of a country and even across national borders, to other political multiparty systems. The approach in this study relies on data that are publicly available, and the simple setup we propose can with some limitations, be generalized to millions of users in other multiparty systems.
AB - This study shows how liking politicians’ public Facebook posts can be used as an accurate measure for predicting present-day voter intention in a multiparty system. We highlight that a few, but selective digital traces produce prediction accuracies that are on par or even greater than most current approaches based upon bigger and broader datasets. Combining the online and offline, we connect a subsample of surveyed respondents to their public Facebook activity and apply machine learning classifiers to explore the link between their political liking behaviour and actual voting intention. Through this work, we show that even a single selective Facebook like can reveal as much about political voter intention as hundreds of heterogeneous likes. Further, by including the entire political like history of the respondents, our model reaches prediction accuracies above previous multiparty studies (60–70%).The main contribution of this paper is to show how public like-activity on Facebook allows political profiling of individual users in a multiparty system with accuracies above previous studies. Beside increased accuracies, the paper shows how such parsimonious measures allows us to generalize our findings to the entire population of a country and even across national borders, to other political multiparty systems. The approach in this study relies on data that are publicly available, and the simple setup we propose can with some limitations, be generalized to millions of users in other multiparty systems.
U2 - 10.1371/journal.pone.0184562
DO - 10.1371/journal.pone.0184562
M3 - Journal article
C2 - 28931023
VL - 12
JO - PLoS ONE
JF - PLoS ONE
SN - 1932-6203
IS - 9
M1 - e0184562
ER -
ID: 186874911