FinSentiA: Sentiment Analysis in English Financial Microblogs

Abstract : The objective of this paper is to report on the building of a Sentiment Analysis (SA) system dedicated to financial microblogs in English. The purpose of our work is to build a financial classifier that predicts the sentiment of stock investors in microblog platforms such as StockTwits and Twitter. Our contribution shows that it is possible to conduct such tasks in order to provide finegrained SA of financial microblogs. We extracted financial entities with relevant contexts and assigned scores on a continuous scale by adopting a deep learning method for the classification. Results show a 0.85 F1Score on a twoclass basis and a 0.62 cosine similarity score.
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal.univ-rennes2.fr/hal-02280169
Contributor : Laurence Leroux <>
Submitted on : Friday, September 6, 2019 - 10:12:44 AM
Last modification on : Saturday, September 7, 2019 - 1:26:03 AM

File

Pages de Actes_TALN2018_vol1.p...
Explicit agreement for this submission

Identifiers

  • HAL Id : hal-02280169, version 1

Citation

Thomas Gaillat, Annanda Sousa, Manel Zarrouk, Brian Davis. FinSentiA: Sentiment Analysis in English Financial Microblogs. Conférence CORIA TALN 2018, Inria Rennes Bretagne-Atlantique; IRISA, May 2018, Rennes, France. ⟨hal-02280169⟩

Share

Metrics

Record views

194

Files downloads

35