Contribution short abstract

Computational Anthropology implies both qualitative and quantitative research processes. Quantitative research depends on sound qualitative research. Quantitative methods are prone to reductionism. Computational methods integrate qualitative and quantitative descriptions, avoiding reductions.

Contribution long abstract

Computational Anthropology is often characterized as purely data-driven; however, it fundamentally implies a rigorous synthesis of both qualitative and quantitative research processes and data. While the influx of data science allows for the observation of social patterns on an unprecedented scale, quantitative metrics alone are frequently insufficient for capturing critical aspects of human behavior and the products of human thought. Traditional quantitative methods have been inherently prone to reductionism—stripping away of complex cultural context in favor of statistically manageable variables. When mathematical models are divorced from the social realities these are designed to represent, these risk producing results that are statistically significant but anthropologically hollow.

Consequently, valid quantitative research is intrinsically dependent on sound qualitative research. Qualitative inquiry provides the "ground truth"—the ethnographic context and theoretical frameworks necessary to define measurements meaningfully and interpret relationships or correlations correctly. Computational methods are a pathway to bridge this divide. Rather than choosing between the breadth of statistics and the depth of ethnography, computational approaches can integrate these descriptions by populating logical and/or mathematical representations with interrelated qualitative and quantitative data.

By utilizing iterative research designs—where qualitative insights inform algorithm and data structure design, and computational patterns retain access to ethnographic sources—researchers can operationalize "thick description" at scale in a comparative manner. This methodological fusion avoids reductionism, ensuring that the complexity of human culture is retained even as it is analyzed through computational means. Ultimately, computational anthropology succeeds not by replacing traditional methods, but by scaling the interpretative power of the discipline.

Contribution short abstract

Based on research in student sex work in Slovenia, this paper argues effective quantitative tools require ethnographic experience. Long-term observation formed the precondition for a questionnaire (n=955). Computer methods are thus extensions of ethnographic work that confirm personal narratives.

Contribution long abstract

In the ongoing discussion on whether up-and-coming computer and quantitative methods are polarising anthropological fieldwork, this paper argues that the most effective quantitative tools are those developed with experience gained in ethnographic fieldwork. Based on research in student sex work in Slovenia, I will demonstrate that years of participant observation and digital ethnography did not only constitute a preliminary phase, but also formed a key precondition to building a good online questionnaire that served as an extension and extra confirmation of fieldwork conclusions.

Research into sensitive topics, which commercial sexuality and vulnerability definitely are, requires a delicate balance. Without previous long-term ethnographic research experience, the following quantitative research would fall victim to reductionism and terminological misunderstandings. I will show how ethnography developed specific vocabulary and exhibited a certain moral geography of the student population, which led to the formulation of a questionnaire answered by 955 respondents. No qualitative method would have been able to reach such a population in such a small time frame.

In the context of researching digital sex work, the researcher never really »leaves« the field. The entanglement of physical and digital reality creates permanent involvement. This paper claims that this inability of permanent disconnection is not a methodological flaw but rather a consequence of digital research. By treating questionnaires as layers of ethnographical research rather than final products, one avoids reductionism. Thus, the author understands computer methods as extensions of ethnographic work that serve to confirm personal narratives and experiences.

Contribution short abstract

How do we preserve ethnographic data integrity with LLMs? This contribution proposes RAG plus GitHub infrastructure enabling LLMs as faithful assistants while maintaining field notes as ground truth, documenting interpretive circularity, and preserving ethical control over sensitive data.

Contribution long abstract

Computational anthropology (CA) faces a foundational tension: how can we leverage artificial intelligence and LLMs to advance qualitative, ethnographic research without reducing lived experience to statistical patterns or introducing hallucinations that compromise fieldwork integrity? This contribution proposes a methodological infrastructure that preserves ethnographic data fidelity while enabling collaborative, computational augmentation of qualitative analysis.

I argue that field notes must remain the epistemological ground truth in human-centered, AI-assisted research. By embedding researcher-collected ethnographic data within RAG systems, LLMs function as faithful interpretive assistants rather than autonomous knowledge generators; they consistently retrieve and contextualize field observations without fabrication. This approach addresses a challenge in CA: enabling quantitative scaling and pattern detection across qualitative datasets while maintaining the thick description, contextual sensitivity, and ethical accountability.

Complementing RAG, collaborative version control systems (such as GitHub) create transparent audit trails for interpretive circularity. As anthropologists iteratively refine codes, annotations, and analytical frameworks, version control preserves the genealogy of interpretation, enabling reflexivity about how field data transform into ethnographic insight. This dual infrastructure addresses the methodological polarisation the roundtable identifies as central to CA's fragmentation, distributing analytical authority while maintaining fidelity to the original field record.

This synthesis avoids both reductionism and particularism: quantitative capabilities emerge from qualitative foundations, and computational tools serve as transparent, auditable extensions of human interpretive work rather than autonomous knowledge engines. Field notes remain irreducible; algorithms remain traceable. This positions CA not as a methodological divide, but as a practice of disciplined, collective knowledge production grounded in the ethnographers' experiences documented.