- 09:45 Welcome; Recent activities of the LAC group
- 10:00 Gabriella Kazai Lumi News AI: A smart reader for a personalised feed of crowd-curated content
- 11:00 [Coffee]
- 11:20 Udo Kruschwitz Enterprise search
- 11:40 Dino Ratcliffe Deep reinforcement learning doom
- 12:00 Chris Fox Existence and Freedom
- 12:20 LAC updates: Quick updates on what everyone in the research group is currently working on
- 12:50 LAC 2016/17 meetings: Discussion as to what subjects to cover in this year's LAC meetings
- 13:00 [Lunch]
- 14:00 Massimo Poesio The DALI project
- 14:40 Chris Madge The markable game
- 15:00 [Coffee]
- 15:20 Silviu Paun Contextual topic models
- 15:40 Annie Louis Conversation Trees
- 16:00 Jon Chamberlain Visualising Discussions: Project update
- 16:20 [Close]
- We plan to have a quick drink on campus afterwards and more drinks later in Wivenhoe.
- Gabriella Kazai - Lumi News AI: A smart reader for a personalised feed of crowd-curated content
Lumi Social News is a content discovery platform and recommender system with iOS and Android app front-ends that builds on crowd curated content and social signals. Lumi automatically builds user profiles from the user's Facebook and/or Twitter public feeds and continually learns from the user's in-app actions. Recommendations of relevant or popular content through various channels are drawn from a large pool of crowd curated content, contributed by the community of Lumi users. Lumi builds on technologies, such as Elastic Search and DynamoDB and a range of machine learning methods including SVM, CF and clustering. In this talk I will detail some of the challenges we face in building a consumer product that can process millions of content posts a day and distribute these to the right users based on their user models and locations.
Gabriella Kazai is VP of Data Science at Lumi, the startup company behind the Lumi social newsreader app that provides personalised recommendations of crowd curated content from across the world's media and social networks. Prior to that, Gabriella worked as a researcher at Microsoft Bing and at Microsoft Research. Her research interests include recommender systems, applied machine learning, information retrieval (IR), crowdsourcing, gamification,data mining, social networks and personal information management, with influences from HCI. She holds a PhD in IR from Queen Mary University of London. She published over 100 research papers and organised several workshops (e.g., GamifIR 2014-2016, News IR 2015) and IR conferences (ICTIR 2009, ECIR 2015-2016, HCOMP 2018). She is one of the founders and organisers of the INEX Book Track 2007-2014 and the TREC Crowdsourcing track 2011-2013.