Location-aware personalized news recommendation with deep semantic analysis
With the popularity of mobile devices and the quick growth of the mobile Web, users can now browse news wherever they want; so, their news preferences are usually related to their geographical contexts. Consequently, many research efforts have been put on location-aware news recommendation, which re...
| Asıl Yazarlar: | , , , |
|---|---|
| Materyal Türü: | Journal article |
| Baskı/Yayın Bilgisi: |
IEEE
2017
|
| _version_ | 1826306669920911360 |
|---|---|
| author | Chen, C Meng, X Xu, Z Lukasiewicz, T |
| author_facet | Chen, C Meng, X Xu, Z Lukasiewicz, T |
| author_sort | Chen, C |
| collection | OXFORD |
| description | With the popularity of mobile devices and the quick growth of the mobile Web, users can now browse news wherever they want; so, their news preferences are usually related to their geographical contexts. Consequently, many research efforts have been put on location-aware news recommendation, which recommends to users news happening nearest to them. Nevertheless, in a real-world context, users’ news preferences are not only related to their locations, but also strongly related to their personal interests. Therefore, in this paper, we propose a hybrid method called location-aware personalized news recommendation with explicit semantic analysis (LP-ESA), which recommends news using both the users’ personal interests and their geographical contexts. However, the Wikipedia-based topic space in LP-ESA suffers from the problems of high dimensionality, sparsity, and redundancy, which greatly degrade the performance of LPESA. To address these problems, we further propose a novel method called LP-DSA to exploit recommendation-oriented deep neural networks to extract dense, abstract, low dimensional, and effective feature representations for users, news, and locations. Experimental results show that LP-ESA and LP-DSA both significantly outperform the state-of-the-art baselines. In addition, LPDSA offers more effective (19:8% to 179:6% better) online news recommendation with much lower time cost (25 times quicker) than LP-ESA. |
| first_indexed | 2024-03-07T06:51:29Z |
| format | Journal article |
| id | oxford-uuid:fcb2e3ce-f7de-471f-bae4-408f6c1ec7a3 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T06:51:29Z |
| publishDate | 2017 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:fcb2e3ce-f7de-471f-bae4-408f6c1ec7a32022-03-27T13:22:57ZLocation-aware personalized news recommendation with deep semantic analysisJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:fcb2e3ce-f7de-471f-bae4-408f6c1ec7a3Symplectic Elements at OxfordIEEE2017Chen, CMeng, XXu, ZLukasiewicz, TWith the popularity of mobile devices and the quick growth of the mobile Web, users can now browse news wherever they want; so, their news preferences are usually related to their geographical contexts. Consequently, many research efforts have been put on location-aware news recommendation, which recommends to users news happening nearest to them. Nevertheless, in a real-world context, users’ news preferences are not only related to their locations, but also strongly related to their personal interests. Therefore, in this paper, we propose a hybrid method called location-aware personalized news recommendation with explicit semantic analysis (LP-ESA), which recommends news using both the users’ personal interests and their geographical contexts. However, the Wikipedia-based topic space in LP-ESA suffers from the problems of high dimensionality, sparsity, and redundancy, which greatly degrade the performance of LPESA. To address these problems, we further propose a novel method called LP-DSA to exploit recommendation-oriented deep neural networks to extract dense, abstract, low dimensional, and effective feature representations for users, news, and locations. Experimental results show that LP-ESA and LP-DSA both significantly outperform the state-of-the-art baselines. In addition, LPDSA offers more effective (19:8% to 179:6% better) online news recommendation with much lower time cost (25 times quicker) than LP-ESA. |
| spellingShingle | Chen, C Meng, X Xu, Z Lukasiewicz, T Location-aware personalized news recommendation with deep semantic analysis |
| title | Location-aware personalized news recommendation with deep semantic analysis |
| title_full | Location-aware personalized news recommendation with deep semantic analysis |
| title_fullStr | Location-aware personalized news recommendation with deep semantic analysis |
| title_full_unstemmed | Location-aware personalized news recommendation with deep semantic analysis |
| title_short | Location-aware personalized news recommendation with deep semantic analysis |
| title_sort | location aware personalized news recommendation with deep semantic analysis |
| work_keys_str_mv | AT chenc locationawarepersonalizednewsrecommendationwithdeepsemanticanalysis AT mengx locationawarepersonalizednewsrecommendationwithdeepsemanticanalysis AT xuz locationawarepersonalizednewsrecommendationwithdeepsemanticanalysis AT lukasiewiczt locationawarepersonalizednewsrecommendationwithdeepsemanticanalysis |