Comment by roddylindsay | Hacker News Reader

Comment by roddylindsay | Hacker News Reader

  For ranking the candidates these predictions are combined into a score by 
  weighting them:
  
  "recap.engagement.is_favorited": 0.5 
  "recap.engagement.is_good_clicked_convo_desc_favorited_or_replied": 11* (the 
  maximum prediction from these two "good click" features is used and weighted by 
  11, the other prediction is ignored). 
  "recap.engagement.is_good_clicked_convo_desc_v2": 11* 
  "recap.engagement.is_negative_feedback_v2": -74 
  "recap.engagement.is_profile_clicked_and_profile_engaged": 12 
  "recap.engagement.is_replied": 27 
  "recap.engagement.is_replied_reply_engaged_by_author": 75 
  "recap.engagement.is_report_tweet_clicked": -369 
  "recap.engagement.is_retweeted": 1 "recap.engagement.is_video_playback_50": 0.005

Who set those weights, and why were they chosen?

"recap.engagement.is_replied": 27 "recap.engagement.is_replied_reply_engaged_by_author": 75

I wonder if this is why threads rank so obnoxiously high. They get artificially boosted by the author replying to their own tweet

isn't that the author replying to a reply on their tweet? so its promoting positive discussion, hence pushing the engagement higher?

Having worked at similar companies on similar systems usually A/B experiments and smaller probability of an action bigger weight it must have to matter much overall. The constants are generally done through some ab tests to get them into reasonable overall behavior but they are a pain to tune and very unlikely optimal in any real sense as it’s often too difficult to do extensive search of them. Like often I’ll see new target have a couple different weights tried on an ab and then maybe second set of experiments after rough magnitude is determined.

Could you link to the code on github?

Reply on news.ycombinator.com