HYPNER a framework for hybrid personalized news recommender systems
The new medium for press release is the online news article publishing over the Internet. Being free from traditional printing limitation, the number of news article made online grow exponentially as new articles are released every subsequent hour. The current problem in the existing news recommende...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2014
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/39292/ http://psasir.upm.edu.my/id/eprint/39292/1/39292.pdf |
| Summary: | The new medium for press release is the online news article publishing over the Internet. Being free from traditional printing limitation, the number of news article made online grow exponentially as new articles are released every subsequent hour. The current problem in the existing news recommender system including the hybrid recommenders is that accuracy is still considerable low. In this paper, we propose HYbrid Personalized NEws Recommender (HYPNER), which is a framework based on ordered clustering and set theory that is able to select news set and generate recommendations that fit the user profiles. We describe how does the framework learn user behavior and interest to predict recommended news set and then discuss it's differences with previous works. |
|---|