Explaining food security warning signals with YouTube transcriptions and local news articles

Food security is a major concern in many countries all over the world. After a relatively long period characterized by a positive trend, the number and severity of food insecurity situations has been growing again in recent years, with alarming projections for the near future. While several Early Warning Systems (EWS) exist to monitor this phenomenon and guide the interventions of governments and ONGs, such systems rely on a narrow set of data types, i.e., mainly satellite imagery and survey data. These data can explain just a limited number of the multiple factors that impact on food security, thus producing an incomplete picture of the real scenario. In this work, we propose a spatio-temporal analysis of unconventional textual data (i.e., YouTube transcriptions and articles from local news papers) to support the explanatory process of food insecurity situations. This data, being completely exogenous to the one used in currently active EWS, can offer a different and complementary perspective on the causes of such crises. We focus on the area of West Africa, which has been at the center of many humanitarian crisis since the beginning of this century. By exploiting state of the art text mining techniques on a corpus of textual documents in French (including video transcriptions extracted from the YouTube channels of four West African news broadcasters and news articles obtained from the online versions of two local newspapers of Burkina Faso) we will analyze food security situations in different regions of the study area in recent years, by also proposing a food security indicator based on textual data, namely TXT-FS.