Close menu

SURE

Sunderland Repository records the research produced by the University of Sunderland including practice-based research and theses.

Quantitative Approach of Geospatial Sentiment Analysis to Reveal Opinions on the War in Ukraine

Prusakiewicz, Chris and McGarry, Kenneth (2023) Quantitative Approach of Geospatial Sentiment Analysis to Reveal Opinions on the War in Ukraine. In: Artificial Intelligence XL 43rd SGAI International Conference on Artificial Intelligence, AI 2023, Cambridge, UK, December 12–14, 2023, Proceedings. Lecture Notes in Computer Science . Springer Nature, pp. 293-306. ISBN 978-3-031-47993-9 (In Press)

Item Type: Book Section

Abstract

The escalation of the full-scale military conict between Russian and Ukrainian forces in February 2022 initiated a worldwide conversation. The manifestation of diverse opinions about the war on Twitter demonstrates a social phenomenon that reveals peoples' perceptions, thoughts, and interactions with war-related information in a digitalised world. Whereas the majority of media outlets in the UK have been following the events in Ukraine, little is known about people's sentiment toward sending military, nancial or medical aid at the regional level. Therefore, this work is to develop a broader understanding of the UK public opinions through Sentiment Analysis (SA) where we collected 2,893 English-language tweets from Twitter API and additional geolocation data is integrated from external sources. The acquired dataset is preprocessed and prepared for textual analysis. In addition to SA, this work compares and contrasts dierent approaches and four selected ML models. Finally, this work uses data visualisation techniques to demonstrate the results from three perspectives; quantitative, temporal, and geospatial. The results
reveal that in the UK, people express on Twitter more negative sentiments
towards the conflict, with a large number of positive tweets towards military and financial issues.

[img] PDF
Prusakiewicz-McGarry.pdf - Accepted Version
Restricted to Repository staff only

Download (1MB) | Request a copy

More Information

Related URLs:
Depositing User: Kenneth McGarry

Identifiers

Item ID: 16525
Identification Number: https://doi.org/10.1007/978-3-031-47994-6
ISBN: 978-3-031-47993-9
URI: http://sure.sunderland.ac.uk/id/eprint/16525
Official URL: http://www.bcs-sgai.org/ai2023/

Users with ORCIDS

ORCID for Kenneth McGarry: ORCID iD orcid.org/0000-0002-9329-9835

Catalogue record

Date Deposited: 12 Sep 2023 12:21
Last Modified: 02 Oct 2024 08:30

Contributors

Author: Kenneth McGarry ORCID iD
Author: Chris Prusakiewicz

University Divisions

Faculty of Technology > School of Computer Science

Subjects

Computing > Data Science
Computing > Artificial Intelligence
Computing

Actions (login required)

View Item (Repository Staff Only) View Item (Repository Staff Only)