In this paper, we propose a methodology to test the integration of political events from the GDELT (Global database of events, language and tone) event database in the fossil fuels equity market prices. Our methodology is based on an approach borrowed from the field of financial time series forecasting. To represent the market to be predicted, we use the PCA technique (principal components analysis) to construct an index statistically representative of our market of interest, based on an equity portfolio. Our results show that political trends calculated on the basis of the political events and geopolitical analysis are features that improve forecasting, compared with delayed mathematical transformations of the time series alone. In the calculation of political trends, we also propose a partition of the international system into geopolitical spheres. As we explain in the article, our methodology represents a first step towards a better quantification of the political risks applied to investment.