What 40,000 Videos Tell Us About The Trending Tab
推荐理由
Here's an excellent video breaking down with extremely compelling data how the "trending" tab is very heavily manipulated
强烈推荐khawkins · 原文
说明
这是2019年由Coffee Break发布的一部评论,主题归在Data science & statistics。它讲的是youtube trending algorithm这一支里的具体问题,而不是把整个领域扫一遍。适合按兴趣直接看、不打算先补课的人。内容上可以概括成:Coffee Break analyzes about 40,000 videos from seven months of YouTube's trending tab. It examines whether trending is biased toward mainstream media and late-night shows.这些读者给出的理由,核心是:Cited in threads on YouTube algorithms and creator complaints as a data-driven look at the trending tab.它贴着当时的技术,看的时候要记得那是那个年份的判断。从2019年到2020年,有3位不同的读者在3个不同月份把它推荐出来,其中明确叫别人去看的有1次。适合已经知道原事件、想听一种解读的人。把它当成观点,而不是教科书。如果已经会了基本定义,就把注意力放在它怎么把youtube trending algorithm变成能跟着复述的例子。
视频信息
- 频道
- Coffee Break
- 时长
- 13 分 50 秒
- 发布年份
- 2019
同主题更多
- A Better Default Colormap for Matplotlib | SciPy 2015 | Nathaniel Smith and Stéfan van der Walt
- DON'T PANIC — Hans Rosling showing the facts about population
- Is Most Published Research Wrong?
- How not to be ignorant about the world | Hans and Ola Rosling
- I don't like notebooks.- Joel Grus (Allen Institute for Artificial Intelligence)
- VisiData Lightning Demo at PyCascades 2018