From the total survey error framework to an error framework for digital traces of humans

Abstract

The interactions and activities of hundreds of millions of people worldwide are recorded as digital traces every single day. When pulled together, these data offer increasingly comprehensive pictures of both individuals and groups interacting on different platforms, but they also allow inferences about broader target populations beyond those platforms, representing an enormous potential for the Social Sciences. Notwithstanding the many advantages of digital traces, recent studies have begun to discuss the errors that can occur when digital traces are used to learn about humans and social phenomena. Incidentally, many similar errors also affect survey estimates, which survey designers have been addressing for decades using error conceptualization frameworks such as the Total Survey Error Framework. In this work, we propose a conceptual framework to diagnose, understand and avoid errors that may occur in studies that are based on digital traces of humans leveraging the systematic approach of the Total Survey Error Framework.

Do News Actually “Find Me”? Using Digital Behavioral Data to Study the News-Finds-Me Phenomenon

“…Particularly, the subsample of 246 Facebook users is arguably even more biased due to self-selection than our starting sample of 1,121 web-tracking panelists (which, notably, already differs in several sociodemographic dimensions from national census statistics; see Online Appendix, Section 1). While respective biases need to be considered with great care (Jürgens et al, 2020;Sen et al, 2019), the consent rate of 22% for the use of the browser plug-in is in line with a previous study (Haim & Nienierza, 2019). 10 Moreover, technical limitations make it impossible to track Facebook use within mobile apps.…”

Collective Emotions during the COVID-19 Outbreak

“…Given that Twitter users are younger, more liberal, have higher formal education than the general population, and include more men (see e.g. Gallotti et al, 2020), future research should therefore assess the generalizability of our findings to larger populations (Sen et al, 2019), for example through representative surveys. Nevertheless, the widespread penetration of social media across countries allows reaching populations traditionally underrepresented in psychological studies, for example low and middle income countries and non-English speakers.…”

Computational personality assessment

“…Putting issues of validity aside, the question of how to best conceptualize affective and cognitive components of personality in an objective manner remains unsolved. The inherent subjectivity of thoughts and feelings, make it very difficult to directly measure them in objective ways (Sen et al, 2019). Related to most extant research, our description of CPA in this manuscript has primarily focused on behavior.…”