Fiche du document
1 juin 2011
- handle: 10670/1.k6psd3
- isbn: 978-3-642-31863-4
- hal: hal-00783287
Mots-clés
human computer interaction information extraction knowledge management sentiment analysis human computer interactionSujets proches
Natural science Sciences Science of scienceCiter ce document
Michel Généreux et al., « Sentiment analysis using automatically labelled financial news », HAL-SHS : linguistique, ID : 10670/1.k6psd3
Métriques
Partage / Export
Résumé
Given a corpus of financial news items labelled according to the market reaction following their publication, we investigate 'cotemporeneous' and forward looking price stock movements. Our approach is to provide a pool of relevant textual features to a machine learning algorithm to detect substantial stock price variations. Our two working hypotheses are that the market reaction to a news item is a good indicator for labelling financial news items, and that a machine learning algorithm can be trained on those news items to build models detecting price movement effectively.