A topic recommendation control method based on topic relevancy and R-tree index
Topic recommendation control aims to suggest relevant topics to users based on their preferences and regional trends. However, existing methods often lack effective measures to evaluate topic-user relevancy and require comparing large amounts of regional information, leading to low accuracy and effi...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitatea Agora
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/114942/1/114942.pdf http://psasir.upm.edu.my/id/eprint/114942/ https://univagora.ro/jour/index.php/ijccc/article/view/6658 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Topic recommendation control aims to suggest relevant topics to users based on their preferences and regional trends. However, existing methods often lack effective measures to evaluate topic-user relevancy and require comparing large amounts of regional information, leading to low accuracy and efficiency. Therefore, we propose a Topic Recommendation Control method based on topic Relevancy and R-tree index (named as TRCRR) to address these limitations. TRCRR introduces a novel personalized topic relevancy metric that quantifies the relevancy between topics and user preferences. To improve efficiency, an R-tree topic index is constructed to organize topics across different regions hierarchically. Experiments on a real-world dataset show that TRCRR achieves better recommendation accuracy and efficiency compared to several baseline methods. The proposed approach offers a promising solution for personalized and region-aware topic recommendation. |
|---|