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.