Abstract
In this paper we study 500 years of African economic history using traveller accounts. We systematically collected 2464 unique documents, of which 855 pass language and rigorous data quality requirements. Our final corpus of texts contains more than 230 000 pages. Analysing such a corpus is an insurmountable task for traditional historians and would probably take a lifetime's work. Applying modern day computational linguistic techniques such as a structural topic model approach (STM) in combination with domain knowledge of African economic history, we analyse how first-hand accounts (topics) evolve across space and time. Apart from obvious accounts of climate, geography, and zoology, we find topics around imperialism, diplomacy, conflict, trade/commerce, health/medicine, evangelization, and many more topics of interest to scholarship. We illustrate how this novel database and text analysis can be employed in three applications (1) What views are introduced by travellers as a result of their occupational background? (2) Did the adoption of quinine as treatment and prophylaxis against malaria facilitate European expansion into Africa? (3) When and how did the diffusion of New World crops alter the African economic landscape?