Joint Local and Global Sequence Modeling in Temporal Correlation Networks for Trending Topic Detection
作者： Kai Shu , Liangda Li , Suhang Wang , Yunhong Zhou , Huan Liu
关键词: Ranking (information retrieval) 、 Data mining 、 Exploit 、 Representation (mathematics) 、 Joint (audio engineering) 、 Search engine 、 Correlation 、 Spike (software development) 、 Sequence 、 Computer science
摘要: Trending topics represent the that are becoming increasingly popular and attract a sudden spike in human attention. critical useful modern search engines, which can not only enhance user engagements but also improve experiences. Large volumes of queries over time indicative aggregated interests thus provide rich information for detecting trending topics. The derived from query logs be naturally treated as temporal correlation network, suggesting both local global signals. signals trending/non-trending within each frequency sequence, denote relationships across sequences. We hypothesize integrating benefit topic detection. In an attempt to jointly exploit complementary networks, we propose novel framework, Local-Global Ranking (LGRank), capture sequence representation with adversarial learning model correlations simultaneously experimental results on real-world datasets commercial engine demonstrate effectiveness LGRank
elsevier.com
sci-hub.st 参考文章(39)
Chi-Hoon Lee, HengShuai Yao, Xu He, Su Han Chan, JieYang Chang, Farzin Maghoul, Learning to predict trending queries Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion. pp. 335- 336 ,(2014) , 10.1145/2567948.2577315
Vasileios Lampos, Andrew C. Miller, Steve Crossan, Christian Stefansen, Advances in nowcasting influenza-like illness rates using search query logs Scientific Reports. ,vol. 5, pp. 12760- 12760 ,(2015) , 10.1038/SREP12760
Ricardo Baeza-Yates, Carlos Hurtado, Marcelo Mendoza, Query recommendation using query logs in search engines extending database technology. pp. 588- 596 ,(2004) , 10.1007/978-3-540-30192-9_58
Gitit Gur-Gershgoren, Sharron Bransburg-Zabary, Eshel Ben-Jacob, Asaf Madi, Yoash Shapira, Dror Y. Kenett, Dynamics of Stock Market Correlations The Czech Economic Review. ,vol. 4, pp. 330- 340 ,(2010)
Eni Mustafaraj, P. Takis Metaxas, Catherine Lui, On the predictability of the U.S. elections through search volume activity ,(2011)
Çaglar Gülçehre, Yoshua Bengio, Yoshua Bengio, Yoshua Bengio, KyungHyun Cho, Junyoung Chung, Empirical evaluation of gated recurrent neural networks on sequence modeling arXiv: Neural and Evolutionary Computing. ,(2014)
Doug Beeferman, Adam Berger, Agglomerative clustering of a search engine query log knowledge discovery and data mining. pp. 407- 416 ,(2000) , 10.1145/347090.347176
Nadav Golbandi Golbandi, Liran Katzir Katzir, Yehuda Koren Koren, Ronny Lempel Lempel, Expediting search trend detection via prediction of query counts Proceedings of the sixth ACM international conference on Web search and data mining - WSDM '13. pp. 295- 304 ,(2013) , 10.1145/2433396.2433435
Chun-Che Wu, Tao Mei, Winston H. Hsu, Yong Rui, Learning to personalize trending image search suggestion international acm sigir conference on research and development in information retrieval. pp. 727- 736 ,(2014) , 10.1145/2600428.2609569
Sepp Hochreiter, Jürgen Schmidhuber, Long short-term memory Neural Computation. ,vol. 9, pp. 1735- 1780 ,(1997) , 10.1162/NECO.1997.9.8.1735