Corporate analysis is needed for various purposes such as finding a good business partner or a good employment, as well as choosing a good investment. Conventionally, it has been based mainly on financial figures. Recent advances in natural language processing technology, however, has activated studies on analysis of non-financial, textual data. This paper tries to predict the growth rate of the operating income of a company from text data contained in the security report of that company. It reports that this method can classify profitable companies and loss-making ones at 55% F-measure.
