Implicit and Explicit Aspect Extraction in Financial Microblogs

Abstract : This paper focuses on aspect extraction which is a sub-task of Aspect-based Sentiment Analysis. The goal is to report an extraction method of financial aspects in microblog messages. Our approach uses a stock-investment taxonomy for the identification of explicit and implicit aspects. We compare supervised and unsupervised methods to assign predefined categories at message level. Results on 7 aspect classes show 0.71 accuracy, while the 32 class classification gives 0.82 accuracy for messages containing explicit aspects and 0.35 for implicit aspects.
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.univ-rennes2.fr/hal-02280371
Contributor : Laurence Leroux <>
Submitted on : Tuesday, September 10, 2019 - 3:22:03 PM
Last modification on : Thursday, September 12, 2019 - 1:20:44 AM

File

W18-3108.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Thomas Gaillat, Bernardo Stearns, Gopal Sridhar, Ross Mcdermott, Manel Zarrouk, et al.. Implicit and Explicit Aspect Extraction in Financial Microblogs. ECONLP: Economics and Natural Language Processing, Jul 2018, Melbourne, Australia. pp.55-61, ⟨10.5281/zenodo.1326536⟩. ⟨hal-02280371⟩

Share

Metrics

Record views

144

Files downloads

18