All kinds of misinformation, some of it dangerous, rose to the top of watchers' feeds. It was during this period that Sargent saw his first flat-earth video. People spent more and more time on the site, and the new code meant small creators and niche content were finding their audience. By 2014, when Susan Wojcicki took over as CEO, the billion-hour goal “was a religion at YouTube, to the exclusion of nearly all else,” as she later told the venture capitalist John Doerr. So Goodrow and the engineers began thirstily hunting for any tiny tweak that would bump watch time upward. It was an audacious goal at the time, people were watching YouTube for only 100 million hours a day, compared to more than 160 million on Facebook and 5 billion on TV. In 2012, YouTube's vice president of product, Shishir Mehrotra, declared that by the end of 2016 the site would hit a billion hours of watch time per day. The recommendation system became increasingly crucial to YouTube's frenetic push for growth. Then the model would predict which videos you'd be most likely to actually watch, and presto: recommendations, more personalized than ever. The model would take your actions (whether you'd finished a video, say, or hit Like) and blend that with other information it had gleaned (your search history, geographic region, gender, and age, for example a user's “watch history” became increasingly significant too). By 2015, they would also introduce neural-net models to craft recommendations. Instead, they focused on “watch time,” or how long viewers stayed with a video it seemed to them a far better metric of genuine interest. Goodrow and his team decided to stop ranking videos based on clicks. Even if a viewer immediately bailed, the click would goose the view count higher, boosting the video's recommendations. Goodrow noticed another problem caused by YouTube's focus on views, which was that it encouraged creators to use misleading tactics-like racy thumbnails-to dupe people into clicking.
In 2011, Google tapped Cristos Goodrow, who was then director of engineering, to oversee YouTube's search engine and recommendation system.
0 kommentar(er)
