Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts
Nowadays, recommender systems (RSes) are becoming increasingly important to individual users and business marketing, especially in the online e-commerce scenarios. However, while the majority of recommendation algorithms proposed in the literature have focused their efforts on improving prediction a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9050785/ |
| _version_ | 1828977232134012928 |
|---|---|
| author | Ya-Hui An Qiang Dong Quan Yuan Chao Wang |
| author_facet | Ya-Hui An Qiang Dong Quan Yuan Chao Wang |
| author_sort | Ya-Hui An |
| collection | DOAJ |
| description | Nowadays, recommender systems (RSes) are becoming increasingly important to individual users and business marketing, especially in the online e-commerce scenarios. However, while the majority of recommendation algorithms proposed in the literature have focused their efforts on improving prediction accuracy, other important aspects of recommendation quality, such as diversity of recommendations, have been more or less overlooked. In the latest decade, recommendation diversity has drawn more research attention, especially in the models based on user-item bipartite networks. In this paper, we introduce a family of approaches to extract fabricated experts from users in RSes, named as the Expert Tracking Approaches (ExTrA for short), and explore the capability of these fabricated experts in improving the recommendation diversity, by highlighting them in a well-known bipartite network-based method, called the Mass Diffusion (MD for short) model. These ExTrA-based models are compared with two state-of-the-art MD-improved models HHP and BHC, with respect to recommendation accuracy and diversity. Comprehensive empirical results on three real-world datasets MovieLens, Netflix and RYM show that, our proposed ExTrA-based models can achieve significant diversity gain while maintain comparable level of recommendation accuracy. |
| first_indexed | 2024-12-14T14:53:42Z |
| format | Article |
| id | doaj.art-ec5f1ec26d0b44eb95463b33d96fb802 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T14:53:42Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ec5f1ec26d0b44eb95463b33d96fb8022022-12-21T22:57:03ZengIEEEIEEE Access2169-35362020-01-018644226443310.1109/ACCESS.2020.29843659050785Improving Recommendation Diversity by Highlighting the ExTrA Fabricated ExpertsYa-Hui An0https://orcid.org/0000-0001-5611-1226Qiang Dong1https://orcid.org/0000-0003-1986-8961Quan Yuan2https://orcid.org/0000-0002-3868-0131Chao Wang3https://orcid.org/0000-0002-3238-0090CompleX Lab, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaCompleX Lab, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaCompleX Lab, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Electrical Engineering, Chongqing University, Chongqing, ChinaNowadays, recommender systems (RSes) are becoming increasingly important to individual users and business marketing, especially in the online e-commerce scenarios. However, while the majority of recommendation algorithms proposed in the literature have focused their efforts on improving prediction accuracy, other important aspects of recommendation quality, such as diversity of recommendations, have been more or less overlooked. In the latest decade, recommendation diversity has drawn more research attention, especially in the models based on user-item bipartite networks. In this paper, we introduce a family of approaches to extract fabricated experts from users in RSes, named as the Expert Tracking Approaches (ExTrA for short), and explore the capability of these fabricated experts in improving the recommendation diversity, by highlighting them in a well-known bipartite network-based method, called the Mass Diffusion (MD for short) model. These ExTrA-based models are compared with two state-of-the-art MD-improved models HHP and BHC, with respect to recommendation accuracy and diversity. Comprehensive empirical results on three real-world datasets MovieLens, Netflix and RYM show that, our proposed ExTrA-based models can achieve significant diversity gain while maintain comparable level of recommendation accuracy.https://ieeexplore.ieee.org/document/9050785/Bipartite networksdiversityfabricated expertsrecommender systems |
| spellingShingle | Ya-Hui An Qiang Dong Quan Yuan Chao Wang Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts IEEE Access Bipartite networks diversity fabricated experts recommender systems |
| title | Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts |
| title_full | Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts |
| title_fullStr | Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts |
| title_full_unstemmed | Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts |
| title_short | Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts |
| title_sort | improving recommendation diversity by highlighting the extra fabricated experts |
| topic | Bipartite networks diversity fabricated experts recommender systems |
| url | https://ieeexplore.ieee.org/document/9050785/ |
| work_keys_str_mv | AT yahuian improvingrecommendationdiversitybyhighlightingtheextrafabricatedexperts AT qiangdong improvingrecommendationdiversitybyhighlightingtheextrafabricatedexperts AT quanyuan improvingrecommendationdiversitybyhighlightingtheextrafabricatedexperts AT chaowang improvingrecommendationdiversitybyhighlightingtheextrafabricatedexperts |