Is the 'Impression Log' Beneficial to Evaluating News Recommender Systems? No, it is Not!
Jeewon AhnHong-Kyun BaeSang-Wook KimPublished in: WWW (Companion Volume) (2024)
Keyphrases
- recommender systems
- collaborative filtering
- news recommendation
- user generated content
- cold start problem
- user profiles
- user preferences
- information overload
- news stories
- news items
- matrix factorization
- news articles
- keywords
- neural network
- information filtering
- user profiling
- topic detection
- online news
- trust aware
- data sets
- user interface
- implicit feedback
- cold start
- learning algorithm
- hot topics
- recommendation quality