2018 UK edition
The Lowry, Salford · 8-9 March 2018
The second UK edition. Ninety-one people were invited back to the same room at The Lowry, and thirty-six accepted. Seventeen sessions ran across two days, keeping the pattern of a short presentation followed by an equal slot for discussion. The programme was broader than the first UK edition: public broadcasters from two countries, a television platform operator, a news publisher, a media agency, sports analysis and university research.
Talks
- “Agent-Based Models: What Happened Next” – A return to the simulation work previewed as a proof of concept at the 2017 UK edition, a year on.
- “Behavioural Machine Learning for Media” – Two academics combined decision theory with machine learning, running sentiment analysis over film subtitles at scale and linking the result to box office, then embedding choice models inside a collaborative-filtering recommender.
- “Attribution” – From a media agency.
- “Analysis of TV Viewing” – From a Nordic public broadcaster.
- “Viewing on the Platform” – From a television platform operator.
- “Discourse Analysis for Content Discovery and Automated Metadata”
- “Social Listening”
- “Analysis in Sport”
- “Challenges in 2018” – A closing group discussion on the second morning.
What we learned
One Title in 540 Survives the Funnel: A study of film sentiment started from 4.7 million titles in a public film database. Of those, 156,568 had subtitle files, 28,943 were long enough to score for sentiment, and 8,768 could be matched to worldwide revenue. Less than one title in 500 reached the modelling stage. The corpus that survives cleaning is the corpus you are actually studying.
Nudges Inside the Recommender: The same work argued that decision theory and machine learning predict the same thing from opposite ends: small artificial choices with strong theory, and large real choices with weak theory. Putting choice-set effects and reference dependence inside a collaborative-filtering model was offered as the hybrid, tested on television content suggestions.