Contrairement à ce que fait plus que suggérer le titre et comme le précise bien l’extrait, il ne s’agit en aucun cas d’une « prédiction » au niveau individuel, mais d’un lien entre variables au niveau du comté (3000 comtés aux É.-U., de 80 à 10 M d’habitants, médiane à 25000)…
Psychological Language on Twitter Predicts County-Level Heart Disease Mortality
▻http://pss.sagepub.com/content/early/2015/01/20/0956797614557867.abstract
Abstract
Hostility and chronic stress are known risk factors for heart disease, but they are costly to assess on a large scale. We used language expressed on Twitter to characterize community-level psychological correlates of age-adjusted mortality from atherosclerotic heart disease (AHD). Language patterns reflecting negative social relationships, disengagement, and negative emotions—especially anger—emerged as risk factors; positive emotions and psychological engagement emerged as protective factors. Most correlations remained significant after controlling for income and education. A cross-sectional regression model based only on Twitter language predicted AHD mortality significantly better than did a model that combined 10 common demographic, socioeconomic, and health risk factors, including smoking, diabetes, hypertension, and obesity. Capturing community psychological characteristics through social media is feasible, and these characteristics are strong markers of cardiovascular mortality at the community level.
L’auteur principal est un jeune et brillant doctorant qui se présente ainsi :
Johannes Eichstaedt
▻http://www.jeichstaedt.com
I am a #data_scientist in psychology. I use Facebook and Twitter to measure the psychological states of large populations, and even small populations. We are characterizing the psychological profiles of communities that support their well-being, or make them sick.
I’m a PhD student in psychology at the University of Pennsylvania under Martin Seligman. In 2011 I co-founded the World Well-Being Project, a team that uses clever Natural Language Processing and machine learning to, well, measure the well-being of the world. Eventually.
#big_data