Negation scope detection in sentiment analysis: Decision support for news-driven trading

Decision support for financial news using natural language processing requires robust methods that process all sentences correctly, including those that are negated. To predict the corresponding negation scope, related literature commonly utilizes rule-based algorithms and generative probabilistic m...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Decision Support Systems Ročník 88; s. 67 - 75
Hlavní autori: Pröllochs, Nicolas, Feuerriegel, Stefan, Neumann, Dirk
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Amsterdam Elsevier B.V 01.08.2016
Elsevier Sequoia S.A
Predmet:
Accuracy
Algorithms
Artificial intelligence
Comparative studies
Computer science
Data mining
Decision support
Decision support systems
Financial news
Learning
Machine learning
Mathematical models
Negation scope detection
News
Rates of return
Raw materials
Reinforcement
Sentences
Sentiment analysis
Sentiment analysis
Negation scope detection
Financial news
Machine learning
Decision support
ISSN:0167-9236, 1873-5797
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Decision support for financial news using natural language processing requires robust methods that process all sentences correctly, including those that are negated. To predict the corresponding negation scope, related literature commonly utilizes rule-based algorithms and generative probabilistic models. In contrast, we propose the use of a tailored reinforcement learning method, since it can conquer learning task of arbitrary length. We then perform a thorough comparison with a two-pronged evaluation. First, we compare the predictive performance using a manually-labeled dataset. Here, reinforcement learning outperforms common approaches from the related literature, leading to a balanced classification accuracy of up to 70.17%. Second, we examine how detecting negation scopes can improve the accuracy of sentiment analysis for financial news, leading to an improvement of up to 10.63% in the correlation between news sentiment and stock market returns. This reveals negation scope detection as a crucial leverage in decision support from sentiment. •Enhance sentiment analysis of financial news by detecting negation scopes•Improvement of up to 10.63% in the correlation between sentiment and stock return•Comparison across different sets of negation words and various methods•Implement reinforcement learning, Hidden Markov models, conditional random fields and rule-based methods
Bibliografia:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0167-9236
1873-5797
DOI:10.1016/j.dss.2016.05.009