Study of the viewers' TV-watching behaviors before, during and after watching a TV program using iot network

摘要

In this paper, we propose to determine whether the viewer's behavior changes or not before, during and after watching a TV program. Are there any behaviors specific to each particular phase of viewing? Here, we propose a flexible and nonintrusive method based on the use of three categories of everyday connected objects (i.e. Smartphone, smartwatch and remote control). Data were collected during participants' interactions with a smart TV i.e. during three phases of viewing a TV program: before, during and after in an uncontrolled environment. A classification of these behaviors was done in order to identify the behaviors of viewers during each phase of TV-watching using a Deep Neural Network (DNN) algorithm, without prior pre-processing of the learning data. The results show that the viewers' behavior is very different from each other during the three phases. Thus, the behavior that was detected in two different phases did not have the same frequency of occurrence for all participants and was not performed by a given viewer with the same duration. In addition, the DNN algorithm gives a good average recognition performance of the three phases: 92.75%, 87.5% and 94% for the first second and third phase respectively. This study can help to better understand the viewers' behavior and anticipate certain actions in order to maintain their attention towards the proposed TV programs.