Abstract
Given a corpus of financial news 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 is a good indicator for labelling financial news, and that a machine learning algorithm can be trained on those news to build models detecting price movement effectively.
| Original language | American English |
|---|---|
| Title of host publication | LREC 2008 Workshop on Sentiment Analysis: Emotion, Metaphor, Ontology and Terminology |
| State | Published - 2008 |