Alleviating Cold Start in the EOSC Recommendations: Extended Page Rank Algorithm
Recommender systems are becoming crucial in academia, where the number of available scientific resources is continuously increasing. One of the main challenges of such systems is a cold start problem, which often occurs when new users have no preference for any items or recommend new items that no c...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10649646/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Recommender systems are becoming crucial in academia, where the number of available scientific resources is continuously increasing. One of the main challenges of such systems is a cold start problem, which often occurs when new users have no preference for any items or recommend new items that no community user has recommended yet. In the case of academic systems, where researchers are usually reluctant to express their explicit feedback or scientific interests, the cold start problem has a considerable and long-term impact on the recommendation algorithms. To alleviate this problem, this paper discusses a graph-based recommendation approach extending the Page Rank algorithm by using a co-authorship network. The proposed approach aims to enhance existing recommendation capabilities in the European Open Science Cloud (EOSC). The first results of the evaluation indicate that the proposed recommendation model is promising and reduces the cold start user-side problem in the academic domain. |
|---|---|
| ISSN: | 2169-3536 |