Social Inequality Observatory
Building interactive support tools for capturing and understanding narratives in socioeconomic history research, as well as analysing and mapping the public perception of social phenomena and the dynamics of online debates and their narratives, such as on inequality, is important for several reasons, both for researchers and policy makers.
MUHAI's Social Inequality Observatory (SIO) is a digital ecosystem of interconnected services, components and interfaces, which allow us to extract, process, explore, enrich and contextualise relations between entities and events, arguments, and other types of narrations extracted from data of different types, retrieved or extracted from a variety of sources, ranging from social media data and scientific knowledge, to general or domain-specific knowledge graphs.
We intend for interested researchers, both academics and citizen scientists, to conduct exploratory studies using the interactive user interfaces that we developed, but also for developers to be able to combine the various AI components we developed and access the datasets and KGs we published in order to build new visualizations, analyses and interfaces.
Data
Narratives, arguments and opinions related to social inequalities are often created, circulated and employed at two distinct but intertwined debate levels that we specifically targeted.
The first one is made by scholarly and scientific debates, which are mostly carried out by academic researchers and field experts, specialised in the measurement, analysis and modeling of inequalities, like inequalities of access to health and care services. The narratives of these scholars and experts can, for example, be captured through peer-reviewed papers, online reports and statistics, like those about between-country inequality of access to COVID-19 vaccines.
The second level includes societal debates, which increasingly reside on online social media and news platforms, and possibly involve millions of participants, mostly non-experts. Societal debates can take place on multiple platforms and through multiple mediums at the same time. These debates and their narratives often focus on the \emph{perceived} causes and effects of salient events, of policies, and issues creating collective interest or concern, like the COVID-19 pandemic and its consequences on inflation, gender balance, or workers’ productivity.
Knowledge Stores
The knowledge contained in the textual datasets is processed using a number of symbolic and statistical AI components, both existing ones and ones developed in the course of the MUHAI project. We developed an ontology and schemas for how the data, its context, the narratives we find in the text and their connection can be stored in knowledge graphs which are interconnected and also connected to existing knowledge sources by other parties, such as the DBpedia knowledge graph. At the moment, we have published two knowledge graphs, one focusing on inequality tweets from the time period of the MUHAI project (OKG), and one focusing on social inequality papers (MIRA-KG).
Interfaces
The ecosystem includes two interfaces that focus on different aspects of the existing data, which query the knowledge graphs and visualize their content in a highly interactive way.
On the one hand, we have developed MIRA, which allows users to (i) turn research questions or paper abstracts into structured and interlinked data, (ii) explore pathways between research question variables to better understand social phenomena, (iii) plot geographical or temporal trends on maps. More about MIRA...
On the other hand, we have developed HERMIONE, which allows users to explore the inequality discourse on twitter through entity co-occurrence networks (here, entities related to inequality) and fine-grained narrative networks. More about Hermione...
Users will be able to develop additional interfaces by querying our knowledge graphs, by developing their own methods or by integrating the AI components published by the MUHAI project.
Become Active
Our data analysis, the knowledge store, as well as the interactive tools are all based on the MUHAI AI components, which are being published in the CANVAS library (currently under development). There components make possible the different tasks in the SIO ecosystem: natural language understanding and textual analysis, interfacing with other knowledge graphs, deep semantic understanding, fine-grained narrative construction, knowledge graph construction and querying, network construction and filtering, interactive visualization of knowledge graphs and narrative networks and their exploration. Interested developers, researchers, and citizens are welcome to (re-)use these components and access our knowledge store to build their own tool for exploring different facets of social inequality.
To learn more about how to get involved with the Social Inequality Observatory Ecosystem, check out other exploration tools in the community tools section or read about how to use our AI components published in the CANVAS library.