Understanding State Preferences with Text as Data: Introducing the UN General Debate Corpus

World leaders have been gathering in New York City in late September every year to address the United Nations General Assembly (UNGA) to present their views on key international issues such as conflict and cooperation, terrorism, development and climate change. The statements of kings, presidents, prime ministers and other leaders are an invaluable and largely untapped source of information on governments’ policy preferences across a wide range of issues over time.
Government preferences are central to the study of international relations and comparative politics. As preferences cannot be directly observed, write ALEXANDER BATURO, NIHEER DASANDI and SLAVA J. MIKHAYLOV, they must be inferred from states’ observed behavior. Although military alliances have been used as an indicator of preference similarity, that approach provides little information about preferences when states do not have alliances. Scholars have instead overwhelmingly relied on UNGA voting records to estimate foreign policy preferences. However, UNGA voting-based methods – like all measures of preference – rely on certain assumptions and, as such, have both strengths and limitations. For example, one shortcoming is that estimates of state preference are derived from the limited number of issues that are voted on in the UNGA in a given year. Therefore, it is essential that researchers can draw on additional data and measures to avoid producing findings about government preferences that are based on one type of observed state behavior.
In their paper "Understanding state preferences with text as data: Introducing the UN General Debate corpus,” the authors argue that the application of text analytic methods to general debate statements can provide much-needed additional measures and tools that can broaden our understanding of government preferences and their effects. The use of text analytic methods is rapidly gaining ground in comparative politics and legislative studies. To date, however, there has been little effort to use speeches to estimate policy preferences in international relations. The formal and institutionalized setting of the general debate, its inclusion of all UN member states, which are provided with equal opportunity to address the Assembly, and the fact that it takes place every year, makes it an ideal resource from which to derive, using text analysis, estimates of state preferences that can be applied to systematic analyses of international politics.
The authors introduce a new dataset, the UN General Debate corpus (UNGDC), consisting of 7314 general debate statements delivered between 1970-2014, that they have preprocessed, categorized and prepared for empirical applications. They begin by discussing the characteristics, content and purpose of the UN general debate and go on to explain the process of collecting and preprocessing the statements and provide an overview of the UNGDC.
The authors then use the text as data approach to show how the UNGDC can be used as a resource from which estimates of government preferences can be derived, providing applications of these estimates. The paper concludes by outlining potential uses of the UNGDC in future research.