Biased Bytes: On the Validity of Estimating Food Consumption from Digital Traces

Video

DOI

Given that measuring food consumption at a population scale is a challenging task, researchers have begun to explore digital traces (e.g., from social media or from food-tracking applications) as potential proxies. The validity of such methods has, however, not been established; it remains unclear to what extent digital traces reflect real food consumption. The present study aims to bridge this gap by quantifying the link between dietary behaviors as captured via social media and via food-tracking applications, at a population scale. We focus on the case of Switzerland and contrast images of consumed foods collected through a food tracking app with food images shared on Twitter, by designing and deploying a novel crowdsourcing framework for estimating biases with respect to nutritional properties and appearance. We find that the food type distributions in social media vs. food tracking diverge; e.g., bread is 2.5 times more frequent among consumed and tracked foods than on Twitter, whereas cake is 12 times more frequent on Twitter. Controlling for the different food type distributions, we contrast consumed and tracked foods of a given type with foods shared on Twitter. For instance, with respect to tastiness, on average across food types, the median dish posted on Twitter ranks among the top 26% of actually consumed and tracked dishes. Across food types, food posted on Twitter is perceived as tastier, more caloric, less healthy, less likely to have been consumed at home, more complex, and larger-portioned, compared to consumed and tracked foods. The fact that there is a divergence between food consumption as measured via the two platforms implies that at least one of the two is not a faithful representation of the true food consumption in the general Swiss population. Thus, researchers should be attentive and aim to establish evidence of validity before using digital traces as a proxy for the true food consumption in the general population. We conclude by discussing the potential sources of these biases and their implications, outlining pitfalls and threats to validity, and proposing actionable ways for overcoming them.