Twitter Using Relevance in Search Results
Twitter has changed the way it presents search results and has begun ranking tweets based on query relevance instead of by timeline recency.
Based on some early trials, the social network indicated that it has seen more engagement in search results and tweets as a result and more time in general is being spent using the service. This is not the first time Twitter has moved away from using the reverse chronological order model it has been known for up to this point; Twitter actually began prioritizing algorithmically "relevant" tweets on the timeline earlier this year.
Twitter's senior software engineer for search quality Lisa Huang explained that while search results were previously presented in reverse chronological order, “the most recent results may not be what the searchers are looking for,” adding that users “could be searching for popular tweets to engage with or to better understand context around the search query, and the most recent tweets are not necessarily best suited for that.”
"A person's behavior on Twitter provides an invaluable source of relevance information," Huang wrote. And Twitter has data showing everything from which tweets you've seen to which tweets you've interacted with and how you interacted with them. "Using this information," Huang continued, "we can train machine learning models that predict how likely a Tweet is to be engaged with."
More on Twitter from Website Magazine: