Speaker Mining -- FAIR Data on Public Broadcasts for Question Answering

2026-06-01

AI Summary

This study addresses the scarcity, fragmentation, and lack of standardization in guest and content metadata within public broadcasting archives, which hinder systematic analysis and question-answering research. To overcome these challenges, the authors propose a scalable FAIR data framework that integrates ZDF archival PDFs, fernsehserien.de, and Wikidata. By combining automated processing with manual curation, they construct a unified knowledge graph and implement a sustainable pipeline for speaker disambiguation and deduplication across heterogeneous sources. The resulting dataset encompasses 31,817 guest mentions, yielding 8,436 canonical individuals and 23,527 appearance records across 6,469 program episodes. The curated data is publicly released at speakermining.wikibase.cloud and interlinked with Wikidata, thereby advancing the large-scale adoption of Linked Open Data in the public broadcasting domain.

Abstract

Public broadcasts are at the center of civic discourse: Traditional television talk shows, alongside emerging podcast and web video formats, capture and guide the attention of our societies, shaping how citizens encounter politics, science, and societal issues. Yet, systematic or even simple analyses of these formats face similar challenges: guest and content metadata are scarce, fleeting, fragmented, and not standardized. Research conducted and questions answered are based on extensive, laborious, yet isolated data-curation efforts that capture only a fraction of the relevant landscape. This work seeks to address this issue using a scaling-oriented framework for FAIR data curation in public broadcasting. Evaluated on 15 broadcasting programs, the pipeline aggregates ZDF Archive PDFs, fernsehserien.de, and Wikidata into a unified knowledge graph. Of the 31,817 candidate guest mentions from these three sources, 17,729 could be automatically disambiguated, further 5,958 via 64 hours of manual reconciling using OpenRefine. Results are published at speakermining.wikibase.cloud and linked to Wikidata, enabling SPARQL-based question answering based on gender, age, occupation, or institutional affiliation across 8,436 canonical persons with 23,527 appearances in 6,469 aligned episodes. Our iterative experience reveals that correctly disambiguating and deduplicating speaker data from heterogeneous sources demands dedicated effort on sustainable infrastructure. For scalable and reliable question answering on public broadcasts to be accessible to everyone, we recommend fostering the potential of linked open data: Advancing alignment and utilization approaches like this work, particularly towards crowdsourced development and curation, but also more FAIR data interfaces from public broadcast service providers.

Problem

• public broadcasts
• metadata scarcity
• FAIR data
• speaker disambiguation
• linked open data

Innovation

• FAIR data
• knowledge graph
• entity disambiguation
• linked open data
• public broadcasting