Smart Analysis of Economics Sentiment in Spanish based on Linguistic Features and Transformers

Texts related to economics and finances are characterized by the use of words and expressions whose meaning (and the sentiments they convey) substantially depend on the context. This poses a major challenge to Natural Language Processing tasks in general, and Sentiment Analysis in particular. For lo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2023-01, Vol.11, p.1-1
Main Authors: Garcia-Diaz, Jose Antonio, Garcia-Sanchez, Francisco, Valencia-Garcia, Rafael
Format: Article
Language:English
Subjects:
Bit error rate
Computerized corpora
Corpus analysis
Data mining
Deep learning
Economic analysis
Feature Engineering
Feature extraction
Financial
Linguistics
Natural language processing
Sentiment analysis
Spanish language
Texts
Transformers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Texts related to economics and finances are characterized by the use of words and expressions whose meaning (and the sentiments they convey) substantially depend on the context. This poses a major challenge to Natural Language Processing tasks in general, and Sentiment Analysis in particular. For low-resource languages such as Spanish, this situation becomes even more acute. Yet, the latest advancements in the field, including word embeddings and transformers, have allowed to boost the performance of Sentiment Analysis solutions. In this work we explore the impact of the combination of different feature sets in the accuracy of Sentiment Analysis in Spanish financial texts. For this, a corpus with 15,915 tweets has been compiled and manually annotated as either positive, negative, or neutral. Then, feature sets based on contextual and non-contextual embeddings along with linguistic features were evaluated both individually and combined. The best results, with a weighted F1-score of 73.15880%, were obtained with a combination of feature sets by means of knowledge integration.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2023.3244065