• Bayesian framework
• The log analysis reveals that the click distributions of individual users are influenced by the local news trend
  • Decompose users news interests
    1. User’s genuine interests (Long-term)
       • Originated from personal characteristics, gender, age, profession, etc.
    2. Local news trends (Short-term)

Baseline

Google News Personalization scalable online collaborative filteringGoogle News Personalization scalable online collaborative filtering
Problems

Scalability
Item Churn


Baseline

Decayed popularity

Result

Increase in CTR by 38% compared between the proposed method and baseline popularity.



Reference

A. S. Das, M. Datar, ...

Results

Improves the CTR upon the existing collaborative method by 30.9%.

Reference

Jiahui Liu, Peter Dolan, and Elin Rønby Pedersen, “Personalized news recommendation based on click behavior,” in Proceedings of the 15th international conference on Intelligent user interfaces - IUI ’10, Hong Kong, China, 2010, p. 31. doi: 10.1145/1719970.1719976.

#recommender-system/news #recommender-system