Discover and read the best of Twitter Threads about #UMAP2020
Most recents (3)
#recsys dataset + paper: "MIND contains 1M users, 160k English news articles and 15.7M impression logs. Every news article contains rich textual content including title, abstract, body, category and entities. " msnews.github.io
"Each impression log contains the click events, non-clicked events and historical news click behaviors of this user before this impression."
Wow! So much data 😳. Awesome! Hope this sparks done interesting research in news recommendation.
Wow! So much data 😳. Awesome! Hope this sparks done interesting research in news recommendation.
With all that data we could've probably fully done our #UMAP2020 paper's analysis on a public dataset 😅 graus.nu/publications/b…
Jaa, filterbubbel, weg met dit op-anekdotes-gestoelde idee 🚮! Met een mention van ons onderzoek met het @FD_Nieuws aanbevelingssysteem: diversere nieuwsconsumptie en meer gelezen artikelen met ons algoritme! villamedia.nl/artikel/het-id… @NickKivits
Meer lezen over ons onderzoek (geschreven door @dsflu met @anca_dmtrch, gepubliceerd bij #UMAP2020 @UMAPconf)? Ziehier: graus.nu/publications/b…
Meer weten over hoe ik denk over filterbubbels? graus.nu/blog/the-filte…
Blij dat we hebben kunnen bijdragen aan deze boodschap! 😅
Blij dat we hebben kunnen bijdragen aan deze boodschap! 😅
Stoked that our paper "Beyond Optimizing for Clicks: Incorporating Editorial Values in News Recommendation" with @dsflu and @anca_dmtrch is accepted as a FULL PAPER at #UMAP2020! I am particularly happy with this publication because... 👇 (1/4) 
1️⃣ In our paper we show how you can align algorithm design across stakeholders (data scientists + journalists), by effectively modeling an editorial value (dynamicness) in a news recommender
2️⃣ we present (more) empirical proof that #recsys (can) offer(s) users more diverse, serendipitous, and dynamic articles compared to editorially curated lists, and hence (can) help in avoiding, not creating filter bubbles!
