In this study, we build on a recent social data scientific mapping of Danish environmentalist organizations and activists during the COVID-19 lockdown in order to sketch a distinct genre of digital social research that we dub a quali-quantitative micro-history of ideas in real-time. We define and exemplify this genre by tracing and tracking the single political idea and activist slogan of grøn genstart across Twitter and other public–political domains. Specifically, we achieve our micro-history through an iterative and mutual attuning between (...) computational and netnographic registers and techniques, in ways that contribute to the nascent field of computational anthropology. By documenting the serial ways in and different steps through which our inquiry was continually fed and enhanced by crossing over from ethnographic observation to computational exploration, and vice versa, we offer up our grøn genstart case account as exemplary of wider possibilities in this line of inquiry. In particular, we position the genre of micro-history of ideas in real-time within the increasingly wide and heterogeneous space of digital social research writ large, including its established concerns with ‘big and broad’ social data, the repurposing of computational ‘interface’ techniques for socio-cultural research, as well as diverse aspirations for deploying digital data within novel combinations of qualitative and quantitative methods. (shrink)

For better and worse, our world has been transformed by Big Data. To understand digital traces generated by individuals, we need to design multidisciplinary approaches that combine social and data science. Data and social scientists face the challenge of effectively building upon each other’s approaches to overcome the limitations inherent in each side. Here, we offer a “data science perspective” on the challenges that arise when working to establish this interdisciplinary environment. We discuss how we perceive the differences and commonalities (...) of the questions we ask to understand digital behaviors, and how our methods may complement each other. Finally, we describe what a path toward common ground between these fields looks like when viewed from data science. (shrink)

According to Clifford Geertz, the purpose of anthropology is not to explain culture but to explicate it. That should cause us to rethink our relationship with machine learning. It is, we contend, perfectly possible that machine learning algorithms, which are unable to explain, and could even be unexplainable themselves, can still be of critical use in a process of explication. Thus, we report on an experiment with anthropological AI. From a dataset of 175K Facebook comments, we trained a neural network (...) to predict the emoji reaction associated with a comment and asked a group of human players to compete against the machine. We show that a) the machine can reach the same accuracy as the players, b) it fails in roughly the same ways as the players, and c) easily predictable emoji reactions tend to reflect unambiguous situations where interpretation is easy. We therefore repurpose the failures of the neural network to point us to deeper and more ambiguous situations where interpretation is hard and explication becomes both necessary and interesting. We use this experiment as a point of departure for discussing how experiences from anthropology, and in particular the tension between formalist ethnoscience and interpretive thick description, might contribute to debates about explainable AI. (shrink)

Big data enables researchers to closely follow the behavior of large groups of individuals by using high-frequency digital traces. However, these digital traces often lack context, and it is not always clear what is measured. In contrast, data from ethnographic fieldwork follows a limited number of individuals but can provide the context often lacking from big data. Yet, there is an under-explored potential in combining ethnographic data with big data and other digital data sources. This paper presents ways that quantitative (...) research designs can combine big data and ethnographic data and account for the synergies that such combinations can provide. We highlight the differences and similarities between ethnographic data and big data, focusing on the three dimensions: individuals, depth of information, and time. We outline how ethnographic data can validate big data by providing a “ground truth” and complement it by giving a “thick description.” Further, we lay out ways that analysis carried out using big data could benefit from collaboration with ethnographers, and we discuss the potential within the fields of machine learning and causal inference. (shrink)

Recent works have suggested an analytical complementarity in mixing big and thick data sources. These works have, however, remained as programmatic suggestions, leaving us with limited methodological inputs on how to archive such complementary integration. This article responds to this limitation by proposing a method for ‘blending’ big and thick analytical insights. The paper first develops a methodological framework based on the cognitivist linguistics terminology of ‘blending’. Two cases are then explored in which blended spaces are crafted from engaging big (...) and thick analytical insights with each other. Through these examples, we learn how blending processes should be conducted as a rapid, iterative and collaborative effort with respect for individual expertise. Further, we demonstrate how the unique, but often overlooked, granularity of big data plays a key role in affording the blending with thick data. We conclude by suggesting four commonly appearing blending strategies that can be applied when relying upon big and thick data sources. (shrink)

Although the rapid growth of digital data and computationally advanced methods in the social sciences has in many ways exacerbated tensions between the so-called ‘quantitative’ and ‘qualitative’ approaches, it has also been provocatively argued that the ubiquity of digital data, particularly online data, finally allows for the reconciliation of these two opposing research traditions. Indeed, a growing number of ‘qualitatively’ inclined researchers are beginning to use computational techniques in more critical, reflexive and hermeneutic ways. However, many of these claims for (...) ‘quali-quantitative’ methods hinge on a single technique: the network graph. Networks are relational, allow for the questioning of rigid categories and zooming from individual cases to patterns at the aggregate. While not refuting the use of networks in these studies, this paper argues that there must be other ways of doing quali-quantitative methods. We first consider a phenomenon which falls between quantitative and qualitative traditions but remains elusive to network graphs: the spread of information on Twitter. Through a case study of debates about nuclear power on Twitter, we develop a novel data visualisation called the modulation sequencer which depicts the spread of URLs over time and retains many of the key features of networks identified above. Finally, we reflect on the role of such tools for the project of quali-quantitative methods. (shrink)