LibRec 每周精选：10篇每个人都应该读的RecSys文章

2018，新年了！祝大家元旦快乐，身体健康，事业有事，家庭和睦！

本周的 LibRec 精选内容如下：

• 10篇每个人都应该读的RecSys文章，以下5篇占了RecSys论文引用的12%。

• Performance of recommender algorithms on top-n testing tasks , 2010. Authors: Paolo Cremonesi , Yehuda Koren , Roberto Turrin

• Trust-aware recommender systems , 2007. Authors: Paolo Massa , Paolo Avesani

• A matrix factorization technique with trust propagation for recommendation in social networks  , 2010. Authors: Mohsen Jamali , Martin Ester

• Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering  , 2010. Authors: Alexandros Karatzoglou , Xavier Amatriain , Linas Baltrunas , Nuria Oliver

• Hidden factors and hidden topics: understanding rating dimensions with review text , 2013. Credit: Julian McAuley , Jure Leskovec

• 10篇每个人都应该读的RecSys文章，以下5篇是自2009年以来最好的Best Paper论文。

• Modeling the Assimilation-Contrast Effects in Online Product Rating Systems: Debiasing and Recommendations , 2017. Authors: X. Zhang, J. Zhao, JCS Lui

• Local Item-Item Models for the Top-N Recommendation , 2016. Authors: E. Christakopoulou and G. Karypis

• Context-Aware Event Recommendation in Event-based Social Networks , 2015. Authors: A. Macedo, L. Marinho and R. Santos

• Beyond Clicks: Dwell Time for Personalization , 2014. Authors: X. Yi, L. Hong, E. Zhong, N. Nan Liu and S. Rajan

• A Fast Parallel SGD for Matrix Factorization in Shared Memory Systems , 2013. Authors: Y. Zhuang, W. Chin, Y. Juan and C. Lin (Best Paper)

• ACM RecSys 10年总结 by Alan Said: http://www.alansaid.com/conferences/recsys/recsys-2017/ 

• 深度学习在推荐系统中的应用：https://medium.com/@libreai/a-glimpse-into-deep-learning-for-recommender-systems-d66ae0681775

• IFUP 2018论文：基于深度学习的 job recommendation, https://arxiv.org/abs/1711.07762 

• ECIR 2018论文：Time-aware novelty metrics for recommender systems，论文：https://t.co/O8EsX4nk5J，代码：https://t.co/O8EsX4nk5J

• 基于Word2Vec的音乐推荐系统：https://towardsdatascience.com/using-word2vec-for-music-recommendations-bb9649ac2484

多说两点：

• 不少朋友关心新版本的LibRec发布时间，开发团队初步预定在农历新年之前。目前团队在紧张地开发多个模块，在各模块开发完成后，还需要时间进行模块的联调、测试等，请大家耐心等待。

• LibRec 新版发布后，开发团队将尝试建立Python接口、增加NLP支持、封装整体解决方案、试水商业应用等多个方面继续提升 LibRec 。有相关技能和兴趣的个人或公司，欢迎与我们联系。