{"type":"ScholarlyArticle","title":"A Comparative Study of Transactional and Semantic Approaches for Predicting Cascades on Twitter","authors":[{"name":"Yunwei Zhao","slug":"yunwei-zhao","given":"Yunwei","family":"Zhao","affiliation":"The National Computer Network Emergency Response Technical Team / Coordination Center of China"},{"name":"Can Wang","slug":"can-wang","given":"Can","family":"Wang","affiliation":"School of Information and Communication Technology , Griffith University , Australia"},{"name":"Chi-Hung Chi","slug":"chi-hung-chi","given":"Chi-Hung","family":"Chi","affiliation":"Data 61 , CSIRO , Australia"},{"name":"Kwok-Yan Lam","slug":"kwok-yan-lam","given":"Kwok-Yan","family":"Lam","affiliation":"School of Computer Science and Engineering , Nanyang Technological University , Singapore"},{"name":"Sen Wang","slug":"sen-wang","given":"Sen","family":"Wang","affiliation":"School of Information and Communication Technology , Griffith University , Australia"}],"abstract":"The availability of massive social media data has enabled the prediction of people’s future behavioral trends at an unprecedented large scale. Information cascades study on Twitter has been an integral part of behavior analysis. A number of methods based on the transactional features (such as keyword frequency) and the semantic features (such as sentiment) have been proposed to predict the future cascading trends. However, an in-depth understanding of the pros and cons of semantic and transactional models is lacking. This paper conducts a comparative study of both approaches in predicting information diffusion with three mechanisms: retweet cascade, url cascade, and hashtag cascade. Experiments on Twitter data show that the semantic model outperforms the transactional model, if the exterior pattern is less directly observable (i.e. hashtag cascade). When it becomes more directly observable (i.e. retweet and url cascades), the semantic method yet delivers approximate accuracy (i.e. url cascade) or even worse accuracy (i.e. retweet cascade). Further, we demonstrate that the transactional and semantic models are not independent, and the performance gets greatly enhanced when combining both.","doi":"10.24963/ijcai.2018/169","url":"https://ijcai.org/proceedings/2018/169","pdf":"https://ijcai.org/proceedings/2018/0169.pdf","markdown":"https://ijcai.org/proceedings/2018/169.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/169","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Computer Vision","track":"Main track","number":169,"pages":{"first":1212,"last":1218},"keywords":["Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Machine Learning Applications: Networks"],"videos":[],"references":[{"position":1,"raw":"[Akbari et al., 2016] Mohammad Akbari, Xia Hu, Nie Liqiang, and Tat-Seng Chua. From tweets to wellness: Wellness event detection from twitter streams. In AAAI'16, pages 87-93, 2016.","title":"From tweets to wellness: Wellness event detection from twitter streams","authors":"Mohammad Akbari, Xia Hu, Nie Liqiang, Tat-Seng Chua","year":"2016","venue":"AAAI'16","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[An et al., 2014] Xiaoran An, Auroop R. Ganguly, Yi Fang, Steven B. Scyphers, Ann M. Hunter, and Jennifer G. Dy. Tracking climate change opinions from twitter data. In KDD'14, pages 1-9, New York, 2014.","title":"Tracking climate change opinions from twitter data","authors":"An","year":"2014","venue":"KDD'14","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bai et al., 2015] Xiang Bai, Song Bai, and Xinggang Wang. Beyond diffusion process: Neighbor set similarity for fast re-ranking. Information Sciences, 325:342 -354, 2015.","title":"Beyond diffusion process: Neighbor set similarity for fast re-ranking","authors":"Xiang Bai, Song Bai, Xinggang Wang","year":"2015","venue":"Information Sciences","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Benhardus and Kalita, 2013] James Benhardus and Jugal Kalita. Streaming trend detection in twitter. International Journal of Web Based Communities, 9:122-139, 2013.","title":"Streaming trend detection in twitter","authors":"Kalita Benhardus, James Benhardus, Jugal Kalita","year":"2013","venue":"International Journal of Web Based Communities","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Blei and Lafferty, 2006] David M. Blei and John D. Laf- ferty. Dynamic topic models. In ICML'06, Pittsburgh, Pennsylvania, USA, 2006.","title":"Dynamic topic models","authors":"David M Blei, John D Lafferty","year":"2006","venue":"ICML'06","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Blei et al., 2003] David M. Blei, Andrew Y. Ng, and Michael I. Jordan. Latent dirichlet allocation. Journal of Machine Learning Research, 3:993-1022, 2003.","title":"Latent dirichlet allocation","authors":"David M Blei, Andrew Y Ng, Michael I Jordan","year":"2003","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bollen et al., 2011] Johan Bollen, Huina Mao, and Xiaojun Zeng. Twitter mood predicts the stock market. Journal of Computational Science, 2:1-8, 2011.","title":"Twitter mood predicts the stock market","authors":"Johan Bollen, Huina Mao, Xiaojun Zeng","year":"2011","venue":"Journal of Computational Science","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Bradley et al., 1999] Margaret M. Bradley, Peter J. Lang, Margaret M. Bradley, and Peter J. Lang. Affective norms for english words (anew): Instruction manual and affective ratings. Center for Research in Psychophysiology, Univer- sity of Florida, Gainesville, Technical Report C-1, 1999.","title":"Affective norms for english words (anew): Instruction manual and affective ratings","authors":"Margaret M Bradley, Peter J Lang, Margaret M Bradley, Peter J Lang","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cheng et al., 2014] Justin Cheng, Lada A. Adamic, P. Alex Dow, Jon Kleinberg, and Jure Leskovec. Can cascades be predicted? WWW'14, pages 925 -936, 2014.","title":"Can cascades be predicted? WWW'14","authors":"Justin Cheng, Lada A Adamic, P Alex Dow, Jon Kleinberg, Jure Leskovec","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Chew and Eysenbach, 2010] Cynthia Chew and Gunther Eysenbach. Pandemics in the age of twitter: Content anal- ysis of tweets during the 2009 h1n1 outbreak. PLoS ONE, 5:e14118, 2010.","title":"Pandemics in the age of twitter: Content analysis of tweets during the 2009 h1n1 outbreak","authors":"Eysenbach Chew, Cynthia Chew, Gunther Eysenbach","year":"2010","venue":"PLoS ONE","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Guerini et al., 2011] Marco Guerini, Carlo Strapparava, and Gozde Ozbal. Exploring text virality in social networks. In ICWSM'11, pages 506-509, Barcelona, Spain, 2011.","title":"Exploring text virality in social networks","authors":"Guerini","year":"2011","venue":"ICWSM'11","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hoang and Mothe, 2017] Thi Bich Ngoc Hoang and Josiane Mothe. Predicting information diffusion on twitter -anal- ysis of predictive features. Journal of Computational Science, pages Available online 28 October 2017, doi = https://doi.org/10.1016/j.jocs.2017.10.010, 2017.","title":"Predicting information diffusion on twitter -analysis of predictive features","authors":"Thi Bich, Ngoc Hoang, Josiane Mothe","year":"2017","venue":"Journal of Computational Science","doi":"10.1016/j.jocs.2017.10.010,2017","url":"https://doi.org/10.1016/j.jocs.2017.10.010,2017","internal_url":null},{"position":13,"raw":"[Hong et al., 2011] Liangjie Hong, Ovidiu Dan, and Brian D. Davison. Predicting popular messages in twitter. In WWW'11, Hyderabad, India, 2011.","title":"Predicting popular messages in twitter","authors":"Hong","year":"2011","venue":"WWW'11","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kobayashi and Lambiotte, 2016] Ryota Kobayashi and Re- naud Lambiotte. Tideh: Time-dependent hawkes process for predicting retweet dynamics. In ICWSM2016, pages 191-200, 2016.","title":"Ryota Kobayashi and Renaud Lambiotte. Tideh: Time-dependent hawkes process for predicting retweet dynamics","authors":"Lambiotte Kobayashi","year":"2016","venue":"ICWSM2016","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Masucci et al., 2011a] Adolfo Paolo Masucci, Alkiviadis Kalampokis, Victor Martínez Eguíluz, and Emilio Hernández-García. Extracting directed information flow networks: An application to genetics and semantics. Phys- ical Review E, 83:026103, 2011.","title":"Extracting directed information flow networks: An application to genetics and semantics","authors":"Masucci","year":"2011","venue":"Physical Review E","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Masucci et al., 2011b] Adolfo Paolo Masucci, Alkiviadis Kalampokis, Victor Martínez Eguíluz, and Emilio Hernández-García. Wikipedia information flow analysis reveals the scale-free architecture of the semantic space. PLoS ONE, 6:e17333, 2011.","title":"Wikipedia information flow analysis reveals the scale-free architecture of the semantic space","authors":"Masucci","year":"2011","venue":"PLoS ONE","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Naaman et al., 2011] Mor Naaman, Hila Becker, and Luis Gravano. Hip and trendy: Characterizing emerging trends on twitter. Journal of the American Society for Information Science and Technology, pages 902-918, 2011.","title":"Hip and trendy: Characterizing emerging trends on twitter","authors":"Mor Naaman, Hila Becker, Luis Gravano","year":"2011","venue":"Journal of the American Society for Information Science and Technology","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sprenger et al., 2013] Timm O. Sprenger, Andranik Tumas- jan, Philipp G. Sandner, and Isabell M. Welpe. Tweets and trades: The information content of stock microblogs. Eu- ropean Financial Management, 20:926--957, 2013.","title":"Tweets and trades: The information content of stock microblogs","authors":"O Timm, Andranik Sprenger, Tumasjan, G Philipp, Isabell M Sandner, Welpe","year":"2013","venue":"European Financial Management","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Takahashi et al., 2011] Toshimitsu Takahashi, Ryota Tomioka, and Kenji Yamanishi. Discovering emerging topics in social streams via link anomaly detection. In ICDM'11, pages 1230-1235, 2011.","title":"Discovering emerging topics in social streams via link anomaly detection","authors":"Toshimitsu Takahashi, Ryota Tomioka, Kenji Yamanishi","year":"2011","venue":"ICDM'11","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Taxidou and Fischer, 2014] Io Taxidou and Peter M. Fis- cher. Online analysis of information diffusion in twitter. In WWW'14, pages 1313-1318, Seoul, Korea, 2014.","title":"Io Taxidou and Peter M. Fischer. Online analysis of information diffusion in twitter","authors":"Fischer Taxidou","year":"2014","venue":"WWW'14","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tononi and Sporns, 2003] Giulio Tononi and Olaf Sporns. Measuring information integration. BMC Neuroscience, 4:31, 2003.","title":"Measuring information integration","authors":"Giulio Tononi, Olaf Sporns","year":"2003","venue":"BMC Neuroscience","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang and Wang, 2007] Xiaojun Wang and Jianwu Wang. Learning information diffusion process on the web. In WWW'07, 2007.","title":"Learning information diffusion process on the web","authors":"Xiaojun Wang, Jianwu Wang","year":"2007","venue":"WWW'07","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2014a] Can Wang, Longbing Cao, Eric Gaussier, and Dan Luo. Coupled behavior representation, modeling, analysis, and reasoning. IEEE Intelligent Systems, 29(4):62-80, 2014.","title":"Coupled behavior representation, modeling, analysis, and reasoning","authors":"Wang","year":"2014","venue":"IEEE Intelligent Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2014b] Sen Wang, Xiaojun Chang, Xue Li, Quan Z. Sheng, and Weitong Chen. Multi-task support vector machines for feature selection with shared knowl- edge discovery. Signal Processing, pages 746-753, 2014.","title":"Multi-task support vector machines for feature selection with shared knowledge discovery","authors":"Wang","year":"2014","venue":"Signal Processing","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2015] Sen Wang, Feiping Nie, Xiaojun Chang, Lina Yao, Xue Li, and Quan Z. Sheng. Unsupervised feature analysis with class margin optimization. ECML- PKDD, pages 383-398, 2015.","title":"Unsupervised feature analysis with class margin optimization","authors":"Sen Wang, Feiping Nie, Xiaojun Chang, Lina Yao, Xue Li, Quan Z Sheng","year":"2015","venue":"ECML-PKDD","doi":null,"url":null,"internal_url":null},{"position":26,"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. SIGKDD'15, pages 1513 -1522, 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":"SIGKDD'15","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhao et al., 2017] Zhou Zhao, Hanqing Lu, Deng Cai, Xi- aofei He, and Yueting Zhuang. Microblog sentiment clas- sication via recurrent random walk network learning. In IJCAI'17, pages 3532-3538, 2017.","title":"Microblog sentiment classication via recurrent random walk network learning","authors":"Zhou Zhao, Hanqing Lu, Deng Cai, Xiaofei He, Yueting Zhuang","year":"2017","venue":"IJCAI'17","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}