Sentiment Classification by Incorporating Background Knowledge from Financial Ontologies

Timen Stepišnik-Perdih, Andraž Pelicon, Blaž Škrlj, Martin Žnidaršič, Igor Lončarski, Senja Pollak


Abstract
Ontologies are increasingly used for machine reasoning over the last few years. They can provide explanations of concepts or be used for concept classification if there exists a mapping from the desired labels to the relevant ontology. This paper presents a practical use of an ontology for the purpose of data set generalization in an oversampling setting, with the aim of improving classification models. We demonstrate our solution on a novel financial sentiment data set using the Financial Industry Business Ontology (FIBO). The results show that generalization-based data enrichment benefits simpler models in a general setting and more complex models such as BERT in low-data setting.
Anthology ID:
2022.fnp-1.3
Volume:
Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Mahmoud El-Haj, Paul Rayson, Nadhem Zmandar
Venue:
FNP
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
17–26
Language:
URL:
https://aclanthology.org/2022.fnp-1.3
DOI:
Bibkey:
Cite (ACL):
Timen Stepišnik-Perdih, Andraž Pelicon, Blaž Škrlj, Martin Žnidaršič, Igor Lončarski, and Senja Pollak. 2022. Sentiment Classification by Incorporating Background Knowledge from Financial Ontologies. In Proceedings of the 4th Financial Narrative Processing Workshop @LREC2022, pages 17–26, Marseille, France. European Language Resources Association.
Cite (Informal):
Sentiment Classification by Incorporating Background Knowledge from Financial Ontologies (Stepišnik-Perdih et al., FNP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.fnp-1.3.pdf