{"type":"ScholarlyArticle","title":"Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks","authors":[{"name":"Bo Wu","slug":"bo-wu","given":"Bo","family":"Wu","affiliation":"Institute of Computing Technology , Chinese Academy of Sciences , China; University of Chinese Academy of Sciences , China"},{"name":"Wen-Huang Cheng","slug":"wen-huang-cheng","given":"Wen-Huang","family":"Cheng","affiliation":"Academia Sinica , Taiwan"},{"name":"Yongdong Zhang","slug":"yongdong-zhang","given":"Yongdong","family":"Zhang","affiliation":"Institute of Computing Technology , Chinese Academy of Sciences , China; University of Chinese Academy of Sciences , China"},{"name":"Qiushi Huang","slug":"qiushi-huang","given":"Qiushi","family":"Huang","affiliation":"University of Surrey , UK"},{"name":"Jintao Li","slug":"jintao-li","given":"Jintao","family":"Li","affiliation":"Institute of Computing Technology , Chinese Academy of Sciences , China"},{"name":"Tao Mei","slug":"tao-mei","given":"Tao","family":"Mei","affiliation":"Microsoft Research , China"}],"abstract":"Prediction of popularity has profound impact for social media, since it offers opportunities to reveal individual preference and public attention from evolutionary social systems. Previous research, although achieves promising results, neglects one distinctive characteristic of social data, i.e., sequentiality. For example, the popularity of online content is generated over time with sequential post streams of social media. To investigate the sequential prediction of popularity, we propose a novel prediction framework called Deep Temporal Context Networks (DTCN) by incorporating both temporal context and temporal attention into account. Our DTCN contains three main components, from embedding, learning to predicting. With a joint embedding network, we obtain a unified deep representation of multi-modal user-post data in a common embedding space. Then, based on the embedded data sequence over time, temporal context learning attempts to recurrently learn two adaptive temporal contexts for sequential popularity. Finally, a novel temporal attention is designed to predict new popularity (the popularity of a new user-post pair) with temporal coherence across multiple time-scales. Experiments on our released image dataset with about 600K Flickr photos demonstrate that DTCN outperforms state-of-the-art deep prediction algorithms, with an average of 21.51% relative performance improvement in the popularity prediction (Spearman Ranking Correlation).","doi":"10.24963/ijcai.2017/427","url":"https://ijcai.org/proceedings/2017/427","pdf":"https://ijcai.org/proceedings/2017/0427.pdf","markdown":"https://ijcai.org/proceedings/2017/427.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/427","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning S-Z","track":"Main track","number":427,"pages":{"first":3062,"last":3068},"keywords":["Machine Learning: Time-series/Data Streams","Machine Learning: Deep Learning","Machine Learning: Learning Preferences or Rankings"],"videos":[],"references":[{"position":1,"raw":"[Beese, 2016] Jennifer Beese. 5 insightful instagram stats that you should know. http://sproutsocial.com/insights/5- instagram-stats/, 2016. [Online].","title":"Jennifer Beese. 5 insightful instagram stats that you should know","authors":"Beese","year":"2016","venue":null,"doi":null,"url":"http://sproutsocial.com/insights/5-instagram-stats/,2016","internal_url":null},{"position":2,"raw":"[Cappallo et al., 2015] Spencer Cappallo, Thomas Mensink, and Cees GM Snoek. Latent factors of visual popularity prediction. In Proc. of ICMR, 2015. [Ellering, 2016] Nathan Ellering. What 16 studies say about the best times to post on social media. http://coschedule.com/blog/best-times-to-post-on-social- media/, 2016. [Online].","title":"Latent factors of visual popularity prediction","authors":"Spencer Cappallo, Thomas Mensink, G M Cees, Snoek","year":"2015","venue":"Nathan Ellering. What 16 studies say about the best","doi":null,"url":"http://coschedule.com/blog/best-times-to-post-on-social-media/,2016","internal_url":null},{"position":3,"raw":"[Gan et al., 2016] Chuang Gan, Chen Sun, Lixin Duan, and Boqing Gong. Webly-supervised video recognition by mutually voting for relevant web images and web video frames. In ECCV, 2016.","title":"Webly-supervised video recognition by mutually voting for relevant web images and web video frames","authors":"Chuang Gan, Chen Sun, Lixin Duan, Boqing Gong","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gelli et al., 2015] Francesco Gelli, Tiberio Uricchio, Marco Bertini, Alberto Del Bimbo, and Shih-Fu Chang. Image popularity prediction in social media using sentiment and context features. In Proc. of ACM MM, 2015.","title":"Image popularity prediction in social media using sentiment and context features","authors":"Francesco Gelli, Tiberio Uricchio, Marco Bertini, Alberto Del Bimbo, Shih-Fu Chang","year":"2015","venue":"Proc. of ACM MM","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ghosh et al., 2016] Shalini Ghosh, Oriol Vinyals, Brian Strope, Scott Roy, Tom Dean, and Larry Heck. Contex- tual lstm (clstm) models for large scale nlp tasks. arXiv preprint arXiv:1602.06291, 2016.","title":"Contextual lstm (clstm) models for large scale nlp tasks","authors":"Shalini Ghosh, Oriol Vinyals, Brian Strope, Scott Roy, Tom Dean, Larry Heck","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[He et al., 2014] Xiangnan He, Ming Gao, Min-Yen Kan, Yiqun Liu, and Kazunari Sugiyama. Predicting the pop- ularity of web 2.0 items based on user comments. In Proc. of SIGIR, pages 233-242, 2014.","title":"Predicting the popularity of web 2.0 items based on user comments","authors":"He","year":"2014","venue":"Proc. of SIGIR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2015] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. arXiv preprint arXiv:1512.03385, 2015.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Khosla et al., 2014] Aditya Khosla, Atish Das Sarma, and Raffay Hamid. What makes an imag e popular? In Proc. of WWW, 2014.","title":"What makes an imag e popular?","authors":"Aditya Khosla, Atish Das Sarma, Raffay Hamid","year":"2014","venue":"Proc. of WWW","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural in- formation processing systems, pages 1097-1105, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Li et al., 2015] Cheng Li, Yue Lu, Qiaozhu Mei, Dong Wang, and Sandeep Pandey. Click-through prediction for advertising in twitter timeline. In Proc. of KDD, 2015.","title":"Click-through prediction for advertising in twitter timeline","authors":"Cheng Li, Yue Lu, Qiaozhu Mei, Dong Wang, Sandeep Pandey","year":"2015","venue":"Proc. of KDD","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Martin et al., 2016] Travis Martin, Jake M Hofman, Amit Sharma, Ashton Anderson, and Duncan J Watts. Exploring limits to prediction in complex social systems. In Proc. of WWW, 2016.","title":"Exploring limits to prediction in complex social systems","authors":"Travis Martin, Jake M Hofman, Amit Sharma, Ashton Anderson, Duncan J Watts","year":"2016","venue":"Proc. of WWW","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[McGrath and Kelly, 1992] Joseph E. McGrath and Janice R. Kelly. Temporal context and temporal patterning. Time & Society, 1(3):399-420, 1992.","title":"Temporal context and temporal patterning","authors":"Joseph E Mcgrath, Janice R Kelly","year":"1992","venue":"Time & Society","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pinto et al., 2013] Henrique Pinto, Jussara M Almeida, and Marcos A Gonc ¸alves. Using early view patterns to predict the popularity of youtube videos. In Proc. of WSDM, pages 365-374, 2013.","title":"Using early view patterns to predict the popularity of youtube videos","authors":"Henrique Pinto, Jussara M Almeida, Marcos A Gonc ¸alves","year":"2013","venue":"Proc. of WSDM","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Qian et al., 2014] Xueming Qian, He Feng, Guoshuai Zhao, and Tao Mei. Personalized recommendation combin- ing user interest and social circle. IEEE Transactions on Knowledge and Data Engineering, 26(7):1763-1777, 2014.","title":"Personalized recommendation combining user interest and social circle","authors":"Xueming Qian, He Feng, Guoshuai Zhao, Tao Mei","year":"2014","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Roy et al., 2013] Suman Deb Roy, Tao Mei, Wenjun Zeng, and Shipeng Li. Towards cross-domain learning for social video popularity prediction. IEEE Transactions on Multi- media, 15(6):1255-1267, 2013.","title":"Towards cross-domain learning for social video popularity prediction","authors":"Deb Suman, Tao Roy, Wenjun Mei, Shipeng Zeng, Li","year":"2013","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Russakovsky et al., 2015] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. Ima- geNet Large Scale Visual Recognition Challenge. IJCV, 115(3):211-252, 2015.","title":"Ima-geNet Large Scale Visual Recognition Challenge","authors":"Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C Berg, Li Fei-Fei","year":"2015","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shamma et al., 2011] David A Shamma, Jude Yew, Lyndon Kennedy, and Elizabeth F Churchill. Viral actions: Pre- dicting video view counts using synchronous sharing be- haviors. In Proc. of ICWSM, 2011.","title":"Viral actions: Predicting video view counts using synchronous sharing behaviors","authors":"Jude David A Shamma, Lyndon Yew, Elizabeth F Kennedy, Churchill","year":"2011","venue":"Proc. of ICWSM","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shen et al., 2014] Hua-Wei Shen, Dashun Wang, Chaoming Song, and Albert-László Barabási. Modeling and predict- ing popularity dynamics via reinforced poisson processes. In Proc. of AAAI, 2014.","title":"Modeling and predicting popularity dynamics via reinforced poisson processes","authors":"Hua-Wei Shen, Dashun Wang, Chaoming Song, Albert-László Barabási","year":"2014","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Srivastava et al., 2014] Nitish Srivastava, Geoffrey E Hin- ton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15, 2014.","title":"Dropout: a simple way to prevent neural networks from overfitting","authors":"Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov","year":"2014","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Szabo and Huberman, 2010] Gabor Szabo and Bernardo A Huberman. Predicting the popularity of online content. Communications of the ACM, 53(8):80-88, 2010.","title":"Predicting the popularity of online content","authors":"Huberman ; ] Gabor Szabo, Bernardo A Szabo, Huberman","year":"2010","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tieleman and Hinton, 2012] T. Tieleman and G. Hinton. Lecture 6.5-RmsProp: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 2012.","title":"Lecture 6.5-RmsProp: Divide the gradient by a running average of its recent magnitude","authors":"T Tieleman, G Hinton","year":"2012","venue":"COURSERA: Neural Networks for Machine Learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2016a] Bo Wu, Wen-Huang Cheng, Yongdong Zhang, and Tao Mei. Time matters: Multi-scale tempo- ralization of social media popularity. In Proc. ACM MM, 2016.","title":"Time matters: Multi-scale temporalization of social media popularity","authors":"Wu","year":"2016","venue":"Proc. ACM MM","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2016b] Bo Wu, Tao Mei, Wen-Huang Cheng, and Yongdong Zhang. Unfolding temporal dynamics: Predict- ing social media popularity using multi-scale temporal de- composition. In Proc. AAAI, 2016.","title":"Unfolding temporal dynamics: Predicting social media popularity using multi-scale temporal decomposition","authors":"Wu","year":"2016","venue":"Proc. AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang and Leskovec, 2011] Jaewon Yang and Jure Leskovec. Patterns of temporal variation in online media. In Proc. of WSDM, 2011.","title":"Patterns of temporal variation in online media","authors":"Jaewon Yang, Jure Leskovec","year":"2011","venue":"Proc. of WSDM","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 1998] Zhengyou Zhang, Michael Lyons, Michael Schuster, and Shigeru Akamatsu. Comparison between geometry-based and gabor-wavelets-based facial expression recognition using multi-layer perceptron. In Proc. of ICCV, pages 454-459. IEEE, 1998.","title":"Comparison between geometry-based and gabor-wavelets-based facial expression recognition using multi-layer perceptron","authors":"Zhang","year":"1998","venue":"Proc. of ICCV","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhao et al., 2015] Qingyuan Zhao, Murat A Erdogdu, Hera Y He, Anand Rajaraman, and Jure Leskovec. Seis- mic, a self-exciting point process model for predicting tweet popularity. In Proc. of KDD, 2015.","title":"Seismic, a self-exciting point process model for predicting tweet popularity","authors":"Qingyuan Zhao, A Murat, Erdogdu, Y Hera, Anand He, Jure Rajaraman, Leskovec","year":"2015","venue":"Proc. of KDD","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}