Application of the random dichotomous classification method to assessment builder’s brand based on consumer’s reviews

The brand influences the success and sustainability of builder. In this paper, authors continue to address problem managing developer branding based on information Internet. paper proposes a dichotomous classification that allows you classify reviews randomly labeled data. he method work with small databases, in contrast methods construction artificial neural networks, which require large samples was implemented "Eidos" system. Eidos system is automated cognitive analysis (ASC-analysis). decision change recall marker made basis changing credibility model by Van Riesbergen's F-measure. application developers' tested example OJSC "Perm Silicate Panels Plant" (PZSP). allowed us distinguish 20 negative 63 positive collected sample. performance adequacy used shown. particular, it shown possible divide textual about into two clusters without prior training. reduces developer's response time reference. This an algorithm for reference clustering method. can be as software collect analyze data, well manage branding.