Here, the watch time is taken into account , i.e. which videos users have watched and for how long. This signal allows us to differentiate the specific content that attracts the most attention of users, and thus offers a more assertive recommendation for the user.
In Google’s words, “If a tennis fan watched 20 minutes of Wimbledon highlight clips and just a few seconds of match analysis videos, we can safely assume they were more interested in watching those highlights. When we first incorporated viewing time into recommendations, we immediately saw a 20% drop in viewing, but we felt it was more important to provide a better experience for viewers.”
Other signals used to determine which videos to show users are their reactions . So if a user has shared or liked a video, they are likely to want to watch other videos of this type. From this, the system predicts belarus business email database how likely the user is to share or like other content, and based on this, it recommends other videos. “If you don’t like a video, it’s a sign that you probably didn’t enjoy watching it ,” Google explains.
Survey Responses: Valuable Watch Time
«To ensure that viewers are satisfied with the content they watch, we measure what we call “valuable viewing time” – the amount of time a user spends watching a video that they find valuable. Valuable viewing time is measured through surveys, where the user is asked to rate the video they watched with a score of one to five stars. This gives us a metric to determine how satisfied the viewer was with the content.»
In these surveys, YouTube also asks the reason for the rating. But these surveys are not always answered, so a machine learning system is incorporated that adds estimated responses , based on those already completed.