Triplétoile: Extraction of knowledge from microblogging text
Vanni Zavarella,
Sergio Consoli,
Diego Reforgiato Recupero,
Gianni Fenu,
Simone Angioni,
Davide Buscaldi,
Danilo Dessí,
Francesco Osborne
Affiliations
Vanni Zavarella
Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, Cagliari, 09121, Italy
Sergio Consoli
European Commission, Joint Research Centre (DG JRC), Via E. Fermi 2749, Ispra (VA), 21027, Italy
Diego Reforgiato Recupero
Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, Cagliari, 09121, Italy; Corresponding author.
Gianni Fenu
Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, Cagliari, 09121, Italy
Simone Angioni
Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, Cagliari, 09121, Italy
Davide Buscaldi
Laboratoire d'Informatique de Paris Nord, Sorbonne Paris Nord University, 99 Av. Jean Baptiste Clement, 93430 Villetaneuse, Paris, France
Danilo Dessí
Knowledge Technologies for Social Sciences Department, GESIS Leibniz Institute for the Social Sciences, Unter Sachsenhausen 6-8, Cologne, 50667, Germany
Francesco Osborne
Knowledge Media Institute, The Open University, Walton Hall, Berrill Building, Milton Keynes, 50667, UK; Department of Business and Law, University of Milano Bicocca, Via Bicocca degli Arcimboldi 8, Milano, 20100, Italy
Numerous methods and pipelines have recently emerged for the automatic extraction of knowledge graphs from documents such as scientific publications and patents. However, adapting these methods to incorporate alternative text sources like micro-blogging posts and news has proven challenging as they struggle to model open-domain entities and relations, typically found in these sources. In this paper, we propose an enhanced information extraction pipeline tailored to the extraction of a knowledge graph comprising open-domain entities from micro-blogging posts on social media platforms. Our pipeline leverages dependency parsing and classifies entity relations in an unsupervised manner through hierarchical clustering over word embeddings. We provide a use case on extracting semantic triples from a corpus of 100 thousand tweets about digital transformation and publicly release the generated knowledge graph. On the same dataset, we conduct two experimental evaluations, showing that the system produces triples with precision over 95% and outperforms similar pipelines of around 5% in terms of precision, while generating a comparatively higher number of triples.
