Yahoo Scientists: “Dwell Time” Is A Better Metric Than Click-Through Rate
Joining the drumbeat against clicks as a flawed metric for user engagement and interest, Yahoo Labs scientists have published a paper that finds time spent on content items — dwell time — is a better indicator of what people enjoy online.
It’s essentially the same argument long made by Chartbeat, the real-time analytics firm that last week announced that “attention minutes” had been accredited by a national metric standards board. Namely, that clicks to a page don’t mean as much as time spent there because people can be fooled by click-bait headlines or just accidentally click to a page before immediately leaving.
Yahoo’s research, which analyzed interaction data on the Yahoo home page, was supportive of that theory, finding that dwell time is “a proxy to user satisfaction for recommended content, and complements or even replaces click-based signals.”
Other findings from the research, reported in a blog post today by Yahoo scientists Liangjie Hong and Suju Rajan:
- Users have less dwell time per article on mobile or tablet devices than on desktops.
- Users spend less time on slideshows than on articles.
- Users dwell more on longer articles, up to 1,000 words. Beyond that limit, there is very little correlation to article length.
- Users dwell the most on articles in the topics of politics or science and the least on articles on food or entertainment.
When the researchers adjusted Yahoo recommendation algorithms to optimize for dwell time instead of clicks, they saw gains in performance, both dwell time and CTR. “One plausible reason is that when optimizing towards dwell-based signals rather than high CTR, users may like the content recommended better, come back to the site and click some more,” they wrote, adding:
This research from the Personalization Science team at Yahoo Labs shows that content recommendation models perform better when using dwell based metrics. Whether these metrics in turn drive long term user engagement such as the number of days a user returns to our site, is another interesting research question that we have studied as well. So, stay tuned for our follow-on post on whether optimizing for dwell time truly drives long term user engagement.