... attendant biases on financial markets, formalizing earlier multi-lingual, corpus-based empirical work that analysed change in sentiment and volume of news in large financial news corpora (Ahmad et al., ... wide web and combined in a variety of ways, including factor analysis and machine learning techniques, to determine when a text contains affective content and what is the polarity of that content ... James G Shanahan, and David A Evans 2004 Coupling niche browsers and affect analysis for an opinion mining application In Proceedings of RIAO-04, pages 186–194 Theresa Wilson, Janyce Wiebe, and...