Logo Lanfrica

World Leaders on Covid-19: A text corpus of leaders' response and personality trait predictions

Domain:

natural language processing

Record type:

dataset
Creator:
Brown, L.HorSte
Editor:
OpeOpe
Publisher:
Uni
Host:avatar
Text corpus and Big Five leadership traits as demonstrated in Brown, Horvath, and Stevens (2021) "Moonshots or a Cautious Take-Off? How the Big Five Leadership Traits Predict Covid Policy Response" (working paper). This dataset covers 26 leaders in “free” or “partly free” countries, according to Freedom House: Australia, Austria, Canada, Chile, Colombia, Denmark, France, Germany, Greece, Hungary, India, Ireland, Italy, Japan, Luxembourg, Mexico, the Netherlands, New Zealand, Norway, Peru, Scotland, South Africa, South Korea, Spain, UK, and the USA. We captured rhetoric from their leaders that referred to “Covid-19” or other similar keywords from press conferences, speeches and statements, interviews, forums with the public, or parliamentary questions. We standardize the context by focusing on a period starting 10 days before the first death officially attributed to the virus in each country and ending 90 days after the first death. We provide: (1) an Overview table overview.xlsx showing countries, leaders, the dates, and the sources of text; (2) merged_corpus_EN.xlsx that merged all text per country, non-English texts processed with Google Translate Ajax API; (3) a python script showing how we generated predictions of Big Five personality traits using the IBM Watson Personality Insights API; and (4) the predicted personality traits per leader in texts_with_big5.pkl The article associated with this dataset is available in ORE at: hdl.handle.net

Similar