ABSTRACT
Digital ethnography extends traditional fieldwork into online platforms, networks, and large-scale data environments, enabling researchers to study social and cultural phenomena that span both physical and virtual spaces. Central to this approach is algorithmic thick description, which combines machine learning and natural language processing to surface patterns across massive datasets while preserving the interpretive richness and contextual nuance characteristic of ethnographic inquiry. The chapter presents concrete strategies for integrating computational tools with ethnographic rigor. Algorithmic refraction, comparison, and triangulation are employed to understand how digital platforms shape social practices and to leverage algorithms as reflexive field devices that support, rather than replace, human insight. In applied contexts, the chapter explores how AI combined with satellite imagery and light detection and ranging (LiDAR) accelerates archaeological discovery and heritage monitoring, demonstrating the importance of on-site validation to maintain empirical grounding. Finally, the chapter proposes circular mixed-methods cycles that integrate computational and interpretive work. Machines generate preliminary patterns, ethnographers interpret underlying mechanisms, and findings iterate between macro-level signals and microlevel meaning, creating a dynamic feedback loop. This framework emphasizes a collaborative, human-centered approach, where AI amplifies the scale and speed of observation while ethnographers retain interpretive authority, ensuring that insights remain grounded in social and cultural context.
