We address the challenge of personalized recommendation of high quality content producers in social media. While some candidates are easily identifiable (say, by being "favorited" many times), there is a long-tail of potential candidates for whom we have little evidence. Through careful modeling of contextual factors like the geo-spatial, topical, and social preferences of users, we propose a tensor-based personalized expert recommendation framework that integrates these factors for revealing latent connections between homogeneous entities (e.g., users and users) and between heterogeneous entities (e.g., users and experts). Through extensive experiments over geo-tagged Twitter data, we find that the proposed framework can improve the quality of recommendation by over 30\% in both precision and recall compared to the state-of-the-art.
%0 Conference Paper
%1 citeulike:14140552
%A Ge, Hancheng
%A Caverlee, James
%A Lu, Haokai
%B Proceedings of the 10th ACM Conference on Recommender Systems
%C New York, NY, USA
%D 2016
%I ACM
%K expert-finding people-recommender recsys2016 tensors
%P 261--268
%R 10.1145/2959100.2959151
%T TAPER: A Contextual Tensor-Based Approach for Personalized Expert Recommendation
%U http://dx.doi.org/10.1145/2959100.2959151
%X We address the challenge of personalized recommendation of high quality content producers in social media. While some candidates are easily identifiable (say, by being "favorited" many times), there is a long-tail of potential candidates for whom we have little evidence. Through careful modeling of contextual factors like the geo-spatial, topical, and social preferences of users, we propose a tensor-based personalized expert recommendation framework that integrates these factors for revealing latent connections between homogeneous entities (e.g., users and users) and between heterogeneous entities (e.g., users and experts). Through extensive experiments over geo-tagged Twitter data, we find that the proposed framework can improve the quality of recommendation by over 30\% in both precision and recall compared to the state-of-the-art.
%@ 978-1-4503-4035-9
@inproceedings{citeulike:14140552,
abstract = {{We address the challenge of personalized recommendation of high quality content producers in social media. While some candidates are easily identifiable (say, by being "favorited" many times), there is a long-tail of potential candidates for whom we have little evidence. Through careful modeling of contextual factors like the geo-spatial, topical, and social preferences of users, we propose a tensor-based personalized expert recommendation framework that integrates these factors for revealing latent connections between homogeneous entities (e.g., users and users) and between heterogeneous entities (e.g., users and experts). Through extensive experiments over geo-tagged Twitter data, we find that the proposed framework can improve the quality of recommendation by over 30\% in both precision and recall compared to the state-of-the-art.}},
added-at = {2017-11-15T17:02:25.000+0100},
address = {New York, NY, USA},
author = {Ge, Hancheng and Caverlee, James and Lu, Haokai},
biburl = {https://www.bibsonomy.org/bibtex/29ca4f4411f93e9f5319946d12164e489/brusilovsky},
booktitle = {Proceedings of the 10th ACM Conference on Recommender Systems},
citeulike-article-id = {14140552},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=2959151},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/2959100.2959151},
doi = {10.1145/2959100.2959151},
interhash = {f94f12261f8898f55842b728f895dce8},
intrahash = {9ca4f4411f93e9f5319946d12164e489},
isbn = {978-1-4503-4035-9},
keywords = {expert-finding people-recommender recsys2016 tensors},
location = {Boston, Massachusetts, USA},
pages = {261--268},
posted-at = {2016-09-18 19:53:17},
priority = {2},
publisher = {ACM},
series = {RecSys '16},
timestamp = {2020-05-03T23:33:10.000+0200},
title = {{TAPER: A Contextual Tensor-Based Approach for Personalized Expert Recommendation}},
url = {http://dx.doi.org/10.1145/2959100.2959151},
year = 2016
}