Forecasting the Accuracy of Forecasters from Properties of Forecasting Rationales

Abstract

Geopolitical forecasting tournaments have stimulated the development of methods for improving probability judgments of real-world events. But these innovations have focused on easier-to quantify variables, like personnel selection, training, teaming, and crowd aggregation—and bypassed messier constructs, like qualitative properties of forecasters’ rationales. Here we adapt methods from natural language processing (NLP) and computational text analysis to identify distinctive reasoning strategies in the rationales of top forecasters, including: (a) cognitive styles, such as dialectical complexity, that gauge tolerance of clashing perspectives and efforts to blend them into coherent conclusions; (b) the use of comparison classes or base rates to inform forecasts; (c) metrics derived from the Linguistic Inquiry and Word Count (LIWC) program. Applying these tools to multiple forecasting tournaments and to forecasters of widely varying skill (from Mechanical Turkers to carefully culled “superforecasters”) revealed that: (a) top forecasters show higher dialectical complexity in their rationales, use more comparison classes, and offer more past-focused rationales; (b) experimental interventions, like training and teaming, that boost accuracy also influence NLP profiles of rationales, nudging them in a “superforecaster-like” direction.