the-algorithm
the-algorithm copied to clipboard
Tweets have a half-life of 360 minutes, which means that a Tweet's relavancy score will decrease by 50% every 6 hours.
Is your feature request related to a problem? Please describe. A clear and concise description of what the problem is. Ex. I'm always frustrated when older Tweets on Twitter become less relavant (and are shown less often to other users) over time. The overall rate at which the relavancy score of older tweets decrease is set at 0.003 The minimal age decay score a tweet can have is 0.6
struct ThriftAgeDecayRankingParams { // the rate in which the score of older tweets decreases 1: optional double slope = 0.003 // the age, in minutes, where the age score of a tweet is half of the latest tweet 2: optional double halflife = 360.0 // the minimal age decay score a tweet will have 3: optional double base = 0.6 }(persisted='true')
Describe the solution you'd like TweetDelete lets you filter and delete tweets based on time. TweetDelete is a free web tool that lets you mass delete your Twitter posts with age and text filters Set TweetDelete for appoximation when no user opens or commits (may be covered under data points)
Do you realize that people live in different timezones in the world?
Asking for a friend
Could you elobarate what it means in code..?
Am I missing something or is the base decay value set at a minimum of .6, therefore we will not see a true half life function decay?
Code References (see using github permalinks)
https://github.com/twitter/the-algorithm/blob/138bb519975407d4ea0dc1478d897d451ef05dab/src/java/com/twitter/search/earlybird/search/relevance/LinearScoringParams.java#L237
https://github.com/twitter/the-algorithm/blob/138bb519975407d4ea0dc1478d897d451ef05dab/src/thrift/com/twitter/search/common/ranking/ranking.thrift#L14-L21