Task 2: Automatic Detection of Narratives from Diplomats of Major Powers

General description

Narratives are causally connected sequences of events that are selected and evaluated as meaningful for a particular audience (Riessman, 2008). They make sense of the world by identifying the significance of people, places, objects, and events in time (Hedling, 2020). In contrast to topics, discourses, or frames, the key feature of narratives is temporality: they possess a causal sequence with beginning, middle, and end, thereby forming a coherent plot that makes them less likely to be challenged and better able to attain emotional identification from their audience (Davis, 2002; Colley, 2020). Through narratives, people connect events that are seemingly unconnected and create expectations about the actors involved and their behavior (Miskimmon et al., 2013). 

In international relations, international actors create strategic narratives to “construct a shared meaning of the past, present, and future of international politics to shape the behavior of domestic and international actors” (Miskimmon et al., 2013, 2017). These narratives have characters or actors (agents); a setting, environment, or space (scene); conflict or action (act); tools and behavior (agencies); and a resolution or goal (purposes). Some authors consider strategic narratives to be a powerful form of propaganda, as they obscure their persuasive intent by embedding messages in a narrative drama (Colley, 2020).

Task 2 is a multiclass multilabel classification problem. Given a series of predefined narratives of each international actor, systems must determine which narrative the tweets belong to. Systems will receive the description of each narrative and a few examples of tweets in both languages (English and Spanish) that belong to each of them (few-shot learning). A tweet may be associated with one, several or none of the narratives.

You will find here the set of narratives used for Task 2.