THE EMPEROR, HITCHCOCK AND PATRIARCHY: AI-ASSISTED VS. HUMAN GENERATED KEY WORDS EXTRACTED FROM UNPROCESSED ETHNOLOGICAL MATERIAL

Archives of audio, video, and written ethnographic materials gathered through individual researchers' field studies often involve data obscured by improper keyword classification that does not accurately reflect their content. This article investigates how a computer information system may assist a professional in this task. We apply a selection of computational intensive methods for the search and clustering of textual materials from the Digital Archive of Ethnological and Anthropological Resources (DAEAR) at the Institute of Ethnology and Anthropology at the University St. Cyril and Methodius in Skopje and comment on their practical usefulness. The results of the machine extraction are compared with the ones obtained from 10 experts (ethnologists and anthropologists) and ten non-experts