Thanks to social media, conversations that happened in (semi-)private settings around the world have moved online. Now, the collective banter, arguments, entreaties, and even hostilities that took place offline are found on multiple platforms such as Twitter, Facebook, Instagram, and more, at a much larger scale. On the one hand, this represents a treasure trove of data that social scientists can leverage to learn about the “ABCs” of humans: attitudes, behaviors, and characteristics. These data can help in (i) assessing theories developed and tested using more traditional methods of studying humans, such as surveys, as well as (ii) conceptualizing new theories, especially those that explain digital aspects of human existence. Although such enormous amounts of observational traces have never before been available and promises for answers to new and old questions abound, they are certainly not a panacea for learning about human ABCs. Studying online human behavior comes with its own set of methodological and technical challenges. It also raises issues of representation and external validity – regarding other online contexts, but specifically to offline settings. Such studies may not only be unfit to (in)validate previously established theories, but when their findings or insights are applied to real-world applications such as policymaking within or beyond sociotechnical systems, biases can be both conceived and reinforced (boyd & Crawford, 2012; Olteanu et al., 2019). Therefore, it is essential to understand the differences between two paradigms of studying human behavior: survey-based methods (SB) and digital trace data (DTD)–based methods.