High Order Bit
summary
Bluefin Labs builds a live-index of TV by strip-mining broadcasts with satellite dishes, linking a semantic content graph to the public social graph and analyzing billions of tweets and posts to connect impressions to expressions. The system, called the TV genome, listens to 20 million people and ingests ~200,000 telecasts and 2 million US ads monthly, adding about 40 million links per month. It surfaces triple-digit year-over-year audience growth for premieres, sentiment and affinity maps for targeting, and cross-channel ad timing that demonstrably correlates TV airings with social activity.
AI-written summary · about
chapters (4)
- 0:00The social TV phenomenon
- 2:01Building the TV genome
- 4:35Analyzing audience sentiment
- 6:38Marketing and future trends
related talks
09mSocial Data and Television
11mThe Value of Social (for) TV
35mData: Faithful or Traitor?
01h 29mShow, Don’t Tell How Data Is Changing Hollywood
27mWhen the Art of Entertainment ties the knot with Science
33mMonitoring a TV streaming service with AI - from PageRank to graph convolutions
23mClick & Watch I
25mHow we bring Performance Marketing to linear TV by using machine learning