a large database from Sambatech3, which has the biggest
online videos platform of Latin America. Its major clients
include SBT, IG, Band, Anhanguera and El Comercio.
We aim to better understand the behavior of multimedia
Web content services, mainly the behavior of this content
consumption. We propose a research with focus on the object
(in our case, the video) being consumed. From this analysis,
we also propose a recommendation model of videos for the
service improvement.
These results have such importance for content providers
and consumers, once they can be used to improve services,
such as online videos recommendation and personalization.
We highlight as main contributions of this work the characterization
and recommendation model with focus on object,
built from different dimensions (e.g., time of consumption
and device kind of access).
This paper is organized as follows: the Section II presents
the related works from our research. Next, in Section III, we
describe the modeling of the Multimedia Web Content platform
studied, as well as the methodology adopted, followed
by Section IV, which contains the dataset description of our
research. We also characterize this data in Section V, that
is the base of the application and evaluation of the recommendation
technique developed in this work, presented in
Section VI. The conclusion of the study is summarized in
Section VII.