Scholarly Wikidata: Population and Exploration of Conference Data in Wikidata using LLMs

TL;DR

This paper proposes to make scholarly data more sustainably accessible by leveraging Wikidata's infrastructure and automating its population in a sustainable manner through LLMs by tapping into unstructured sources like conference Web sites and proceedings texts as well as already existing structured conference datasets.

Abstract

Several initiatives have been undertaken to conceptually model the domain of scholarly data using ontologies and to create respective Knowledge Graphs. Yet, the full potential seems unleashed, as automated means for automatic population of said ontologies are lacking, and respective initiatives from the Semantic Web community are not necessarily connected: we propose to make scholarly data more sustainably accessible by leveraging Wikidata's infrastructure and automating its population in a sustainable manner through LLMs by tapping into unstructured sources like conference Web sites and proceedings texts as well as already existing structured conference datasets. While an initial analysis shows that Semantic Web conferences are only minimally represented in Wikidata, we argue that our methodology can help to populate, evolve and maintain scholarly data as a community within Wikidata. Our main contributions include (a) an analysis of ontologies for representing scholarly data to identify gaps and relevant entities/properties in Wikidata, (b) semi-automated extraction -- requiring (minimal) manual validation -- of conference metadata (e.g., acceptance rates, organizer roles, programme committee members, best paper awards, keynotes, and sponsors) from websites and proceedings texts using LLMs. Finally, we discuss (c) extensions to visualization tools in the Wikidata context for data exploration of the generated scholarly data. Our study focuses on data from 105 Semantic Web-related conferences and extends/adds more than 6000 entities in Wikidata. It is important to note that the method can be more generally applicable beyond Semantic Web-related conferences for enhancing Wikidata's utility as a comprehensive scholarly resource. Source Repository: https://github.com/scholarly-wikidata/ DOI: https://doi.org/10.5281/zenodo.10989709 License: Creative Commons CC0 (Data), MIT (Code)

Figures (6)

• Figure 1: Overview of the methodology. The code used for the process including the LLM prompts, SPARQL queries, OpenRefine schemas are available in the GitHub repository.
• Figure 2: An example use of qualifiers in ISWC 2023 Wikidata entity (Q119153957).
• Figure 3: Screenshot from Scholia for a panel on the page for the ESWC conference series https://scholia.toolforge.org/event-series/Q17012957#top-topic-through-time.
• Figure 4: Screenshot from Scholia for the co-author graph panel on the page for the ISWC 2023 conference. All co-authorships are shown, also those beyond the specific conference. It shows only part of the graph and the photographs of people have been removed (due to copyright). For the interactive complete graph, please refer to https://scholia.toolforge.org/event/Q119153957#co-authors.
• Figure 5: Screenshots from Synia showing the number of participants and acceptance rates of ISWC through time. From https://synia.toolforge.org/#scientificeventseries/Q6053150.