%0 Journal Article %1 Yang2019 %A Yang, Qiang %A Li, Zhixu %A Liu, An %A Liu, Guanfeng %A Zhao, Lei %A Zhang, Xiangliang %A Zhang, Min %A Zhou, Xiaofang %D 2019 %J World Wide Web %K academic-reference recommender %N 6 %P 2499--2517 %R 10.1007/s11280-019-00687-9 %T A novel hybrid publication recommendation system using compound information %U https://doi.org/10.1007/s11280-019-00687-9 %V 22 %X Publication recommendation is an interesting but challenging research problem. Most existing studies only use partial information of papers' contents, reference network or co-author relationship, which leads to an unsatisfied recommendation result. In this study, we propose a novel hybrid publication recommendation approach using compound information which retrieves top-K most relevant papers from a publication depository for a set of user input keywords. Our advantages comparing to the existing methods include: (1) Reaching a better recommendation results by taking the advantages of both content-based recommendation and citation-based recommendation and exploring much richer information of papers in one method; (2) Effectively solving the cold-start problem for new published papers by considering the vitality of papers and the impact factor of venues into the citation network; (3) Saving a large overhead in calculating the content-based similarity between papers and user input keywords by doing paper clustering based on the citation network. Extensive experiments on DBLP and Microsoft Academic datasets demonstrate that PubTeller improves the state-of-the-art methods with 4\% in Precision and 4.5\% in Recall.

@article{Yang2019, abstract = {Publication recommendation is an interesting but challenging research problem. Most existing studies only use partial information of papers' contents, reference network or co-author relationship, which leads to an unsatisfied recommendation result. In this study, we propose a novel hybrid publication recommendation approach using compound information which retrieves top-K most relevant papers from a publication depository for a set of user input keywords. Our advantages comparing to the existing methods include: (1) Reaching a better recommendation results by taking the advantages of both content-based recommendation and citation-based recommendation and exploring much richer information of papers in one method; (2) Effectively solving the cold-start problem for new published papers by considering the vitality of papers and the impact factor of venues into the citation network; (3) Saving a large overhead in calculating the content-based similarity between papers and user input keywords by doing paper clustering based on the citation network. Extensive experiments on DBLP and Microsoft Academic datasets demonstrate that PubTeller improves the state-of-the-art methods with 4{\%} in Precision and 4.5{\%} in Recall.}, added-at = {2019-11-27T17:52:18.000+0100}, author = {Yang, Qiang and Li, Zhixu and Liu, An and Liu, Guanfeng and Zhao, Lei and Zhang, Xiangliang and Zhang, Min and Zhou, Xiaofang}, biburl = {https://www.bibsonomy.org/bibtex/26f68cf1e787a308d1fd13c89afef0f53/brusilovsky}, day = 01, description = {A novel hybrid publication recommendation system using compound information | SpringerLink}, doi = {10.1007/s11280-019-00687-9}, interhash = {775d8240be9ef3aa97d53ce74b700e90}, intrahash = {6f68cf1e787a308d1fd13c89afef0f53}, issn = {1573-1413}, journal = {World Wide Web}, keywords = {academic-reference recommender}, month = nov, number = 6, pages = {2499--2517}, timestamp = {2019-11-27T17:52:18.000+0100}, title = {A novel hybrid publication recommendation system using compound information}, url = {https://doi.org/10.1007/s11280-019-00687-9}, volume = 22, year = 2019 }