RAMOS, F. B. A.; http://lattes.cnpq.br/3071265324776966; RAMOS, Felipe Barbosa Araújo.
Abstract:
mmendation systems have been used in several application domains, most recently for
TV (Digital TV, Smart TV, etc). Several existing approaches can be used to recommend
items or tags, mainly based on user feedback. However, in the Digital TV domain, user
feedback has to be done generally by using the remote control, which should be avoided to improve user experience. Moreover, in the Smart TV environment several types of items
can be recommended (movies, music, books, etc). Thus, the recommendation should be
generic enough to suit to different content. Therefore, to solve the problem of acquiring
feedback and still generate personalized recommendations to be used by different Smart
TV applications, this work proposes a recommendation architecture based on the extraction and classification of terms by analyzing the textual descriptions of TV programs present on electronic programming guides. In order to validate the proposed solution, a prototype using a real dataset has been developed, showing that from the recommended terms is possible to generate final recommendations for different Smart TV applications