While social media invent various algorithms to show relevant information to users, companies like Buffer are trying to understand how to circumvent these algorithms to promote their clients’ content. This is not necessarily a zero-sum game, as it may seem. Optimizers add more structure to the content, pick relevant addressees, and distribute content to the media where information overload is less extreme.
The simplest problem around is to pick the best time for posting when you already have certain content. I looked into this once for StackExchange.com, and the optimal timing happened to depend a lot on the subsite in question. StackExchange is a network of Q&A websites built on a common technology but with somewhat segregated users and different rules. The subsites look alike, integrated, and you normally expect the common features to prevail over everything else. But according to the data, the patterns of performance, such as time-to-answer, vary across the subsites. The soft rules—those that are not engraved in the common software code—and people make them vary.
Here’s another example: Y-Combinator’s Hacker News, which has a solid community and transparent ranking algorithm. The rules are simple: a user submits a link and title, the community upvote this submission. Good submissions make the front page, bad submissions are unread and forgotten. The service receives more than 300,000 submissions annually. The question is the same: given a submission, what’s the best time to post it? I took the number of expected upvotes as the criterion.
Many studied the Hacker News dataset before. A good example is this one. There’s even a special app for picking the time (I didn’t get what it does exactly). They answered different questions, though.
Here’s my version of events. In this post, however, I’d make another point based on this data.
First, just looking at upvotes shows that weekends are the better days for posting (0 is Monday, 6 is Sunday):
However, this approach can’t say much. Time affects not only users who read links submitted to Hacker News (demand), but also those who submit the links (supply). You have causation suspects right away. Like, maybe users submit better links on weekends because they have more time to pick the good ones. Then scheduling the same submission of yours to weekends would not increase the upvotes it gets.
For a bunch of typical reasons (few variables available, unstructured data, and no suitable natural experiments), the impact of time on upvotes is hard to separate from other factors. You have only indirect evidences. For example, less competition on weekends may increase expected upvotes:
It remains unclear how to sum up indirect evidences into conclusions. Statistical models would disappoint. Time-related variables explain less than 1% of variation—meaning, unsurprisingly, that the other 99% depend on something else. This something includes the page you link to, the readers, and nuances of Hacker News’ architecture.
My point is, even a simple algorithm can be efficient, meaning, its outcome is independent of irrelevant factors, like time. A complex algorithm may perform worse, in fact. If content promotion depends on the author’s social capital (followers, friends, subscribers), ranking relies on the author’s past submissions rather than the current one. So, Facebook’s or Quora’s algorithms for sorting things for users are not only harder to pass through; they also may distort important outcomes.