Hilary Mason interviewed at Web 2.0 Summit 2011

on YouTube ↗06m

" summary

bitly presents a clear claim: URL attention decays differently by content and network, with a measured half-life study showing YouTube 7 hours vs Twitter 2.8; geo‑relevance is computed by location distributions and entropy to flag regionally salient documents; work focuses on realtime search and matching content to interested readers; tools actually used include bash and Python ecosystem (numpy, scipy, scikit‑learn, pandas), Hadoop for offline analysis, and visualization via geffy.

AI-written summary · about

" related talks

• 27mPrasad Yalamanchi: CEO of HIDDIME.COM – Cloud Analytics Service at Cypher 2017Prasad Yalamanchi · Cypher 2017
• 40mThe Echo-Chamber of Your Social Media FeedTamar Yastrab · PyData New York City 2019
• 05mCameron Marlow at Social Graph Foo Camp, February 2008Cameron Marlow · Social Graph Foo Camp 2008
• 31mReal time association mining in large social networksBen Chamberlain · PyData London 2016
• 39mLive-Hack: Analyzing 7 years of Buzzwords at Scale #bbuzzChristoph Tavan · Berlin Buzzwords 2016
• 05mHjalmar Gislason interviewed at Web 2.0 Expo San Francisco 2011Hjalmar Gislason · Web 2.0 Expo San Francisco 2011
• 40mLevel Up: Everything you need to know about search, ...Grant Ingersoll · Berlin Buzzwords 2016
• 23mML-Powered Search & Recommendation 101Sergey Polyashov · Conf42 Machine Learning 2025