Benefits of using ranking skip-gram techniques for opinion mining approaches

This paper presents an opinion mining approach in the domain of Social TV using two different contexts: Twitter user messages for Spanish and English, as well as movie reviews. The main goal of this paper is to study the benefits of opinion mining approaches using ranking skip-gram techniques for processing user feedbacks. To carry out this study it is described a system based on supervised machine learning and text categorisation techniques. This system has been evaluated on user messages obtained from Twitter and Amazon users´ reviews. Results demonstrate that the use of ranking skip-grams techniques provide suitable opinion mining results independently of the language and scenario of application. The paper also presents information about business benefits of these technologies which are part of an advanced digital media delivery platform currently under development in the framework of the EU-funded project SAM - Socialising Around Media.