Event Detection in News Articles: A Hybrid Approach Combining Topic Modeling, Clustering, and Named Entity Recognition

Nikos Kapellas, Sarantos Kapidakis

2023

Abstract

This research presents a comprehensive analysis of news articles with the primary objectives of exploring the underlying structure of the data and detecting events contained within news articles. The study collects articles from Greek online newspapers and focuses on analyzing a sub-set of this data, related to a predefined news topic. To achieve this, a hybrid approach that combines topic modeling, feature extraction, clustering, and named entity recognition, is employed. The obtained results prove to be satisfactory, as they demonstrate the effectiveness of the proposed methodology in news event detection and extracting relevant contextual information. This research provides valuable insights for multiple parties, including news organizations, researchers, news readers, and decision-making systems, as it contributes to the fields of event detection and clustering. Moreover, it deepens the understanding of applying solutions that do not require explicit human intervention, to real-world language challenges.

Paper Citation

in Harvard Style

Kapellas N. and Kapidakis S. (2023). Event Detection in News Articles: A Hybrid Approach Combining Topic Modeling, Clustering, and Named Entity Recognition. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD; ISBN 978-989-758-671-2, SciTePress, pages 272-279. DOI: 10.5220/0012234300003598

in Bibtex Style

@conference{keod23,
author={Nikos Kapellas and Sarantos Kapidakis},
title={Event Detection in News Articles: A Hybrid Approach Combining Topic Modeling, Clustering, and Named Entity Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD},
year={2023},
pages={272-279},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012234300003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD
TI - Event Detection in News Articles: A Hybrid Approach Combining Topic Modeling, Clustering, and Named Entity Recognition
SN - 978-989-758-671-2
AU - Kapellas N.
AU - Kapidakis S.
PY - 2023
SP - 272
EP - 279
DO - 10.5220/0012234300003598
PB - SciTePress