Comparable English-Russian book review corpora for sentiment analysis

We present newly-produced comparable corpora of book reviews in English and Russian. The corpora are comparable in terms of domain, style and size. We are using them for cross-lingual experiments in document-level sentiment classi?cation. Quantitative analyses of the corpora and the language di?erences they exhibit highlight a number of issues that must be considered when developing systems for automatic sentiment classi?cation. We also present experiments with a sentiment classi?cation system applied to the corpora. The results suggest that di?erences in the way that sentiment is expressed in the two languages lead to large di?erence in sentiment classi?cation accuracy.