Virtual RecSysNL on News and Media

[UPDATE: new schedule and zoom link]

Dear RecSysNL members, we're happy to announce our second (and last?) virtual meetup! On Tuesday June 8th, we will host a meetup focused on news and media, both in terms of evaluation and production implementation. As usual we have one academic guest speaker, and one speaker from industry....details below. Hope to see you there!

------------ SCHEDULE ------------
19:00-19:05 Meetup starts
19:05-19:20 Community section: 🇳🇱 ACM RecSys 2021 Announcements
19:20-19:50 Talk 1: News recommenders with a (democratic) mission - Sanne Vrijenhoek (UvA)
19:50-20:20 Talk 2: Serverless Data Processing - Aron Hammond (DPG Media)

------------ ABSTRACTS ------------

Abstract: News recommenders with a (democratic) mission - Sanne Vrijenhoek, Project Researcher, University of Amsterdam
News recommenders have the potential to help users filter the enormous amount of news that is available online, and as such may play an important role in determining what information users do and do not get to see. However, current approaches to evaluating recommender systems are often focused on measuring an increase in user clicks and short-term engagement, rather than measuring the user's and society’s longer term interest in diverse and important recommendations. In this talk we aim to bridge the gap between so-called normative notions of news diversity, as it is known in social sciences and specifically democratic theory, and quantitative metrics necessary for evaluating the recommender system. We discuss a number of democratic missions a recommender system could have, together with a set of evaluation metrics stemming from these missions, and suggest ways for practical implementations of these metrics.

Abstract: Serverless Data Processing at DPG Media - Aron Hammond - Machine Learning Engineer
The talk will be about practical considerations that our team has had to make in order to bring a recommender system into production. I’ll cover the “default” tools with which we started (Batch processing in Spark) and follow that up with more recent tools like AWS Lambda and Spark Streaming.