OKG: A Knowledge Graph for Fine-grained Understanding of Social Media Discourse on Inequality

In recent years, social media platforms such as Twitter have allowed people to voice their opinions by engaging in online discussions. The availability of such discussions has garnered interest amongst researchers in analyzing the dynamics on critical topics, such as inequality. Most of the current strategies are, however, limited with respect to conveying the fine-grained opinions of users, focusing on tasks such as sentiment analysis or topic modeling that extract coarse categorizations. In this work, we address this challenge by integrating a Twitter corpus with the output of finer-grained semantic parsing for the analysis of social media discourse. To do so, we first introduce the OBservatory Integrated Ontology (OBIO) that integrates social media metadata with various types of linguistic knowledge. We then present the Observatory Knowledge Graph (OKG), a knowledge graph in terms of the ontology, populated with tweets on inequality. We lastly provide use cases showing how the knowledge graph can be used as the backbone of a social media observatory, to facilitate a deeper understanding of social media discourse.