Adaptive User Engagement Evaluation via Multi-task Learning
作者： Hamed Zamani , Pooya Moradi , Azadeh Shakery
关键词: Function (engineering) 、 Web application 、 Social network 、 Transfer of learning 、 Computer science 、 User engagement 、 World Wide Web 、 Recommender system 、 Task (project management) 、 Multi-task learning
摘要: User engagement evaluation task in social networks has recently attracted considerable attention due to its applications recommender systems. In this task, the posts containing users' opinions about items, e.g., tweets ratings movies IMDb website, are studied. paper, we try make use of from different web improve user performance. To aim, propose an adaptive method based on multi-task learning. Since paper study problem detecting with positive which is a highly imbalanced classification problem, modify loss function learning algorithms cope data. Our evaluations over dataset including four diverse and popular data sources, i.e., IMDb, YouTube, Goodreads, Pandora, demonstrate effectiveness proposed method. findings suggest that transferring knowledge between sources can
acm.org
sci-hub.se 参考文章(12)
Simon Dooms, Toon De Pessemier, Luc Martens, Mining cross-domain rating datasets from structured data on twitter Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion. pp. 621- 624 ,(2014) , 10.1145/2567948.2579232
David Martin Ward Powers, None, Evaluation: from Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation arXiv: Learning. ,vol. 2, pp. 37- 63 ,(2011)
Rehan Akbani, Stephen Kwek, Nathalie Japkowicz, Applying support vector machines to imbalanced datasets european conference on machine learning. ,vol. 3201, pp. 39- 50 ,(2004) , 10.1007/978-3-540-30115-8_7
Jianhui Chen, Lei Tang, Jun Liu, Jieping Ye, A convex formulation for learning shared structures from multiple tasks Proceedings of the 26th Annual International Conference on Machine Learning - ICML '09. pp. 137- 144 ,(2009) , 10.1145/1553374.1553392
Daniele Loiacono, Andreas Lommatzsch, Roberto Turrin, An analysis of the 2014 RecSys Challenge conference on recommender systems. pp. 1- 6 ,(2014) , 10.1145/2668067.2668082
Jianhui Chen, Ji Liu, Jieping Ye, Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks ACM Transactions on Knowledge Discovery From Data. ,vol. 5, pp. 22- 22 ,(2012) , 10.1145/2086737.2086742
Zhi Liu, Qihang Wu, Yun Zhang, CL Philip Chen, None, Adaptive least squares support vector machines filter for hand tremor canceling in microsurgery International Journal of Machine Learning and Cybernetics. ,vol. 2, pp. 37- 47 ,(2011) , 10.1007/S13042-011-0012-5
Ibrahim Uysal, W. Bruce Croft, User oriented tweet ranking Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11. pp. 2261- 2264 ,(2011) , 10.1145/2063576.2063941
Miles Osborne, Sasa Petrovic, Victor Lavrenko, RT to Win! Predicting Message Propagation in Twitter international conference on weblogs and social media. pp. 586- 589 ,(2011)
José G. C. de Souza, Hamed Zamani, Matteo Negri, Marco Turchi, Falavigna Daniele, Multitask Learning for Adaptive Quality Estimation of Automatically Transcribed Utterances north american chapter of the association for computational linguistics. pp. 714- 724 ,(2015) , 10.3115/V1/N15-1073