Online social network is generating information at an explosive rate. Information competes with each other for people’s limite attention. How people’s attention to information evolves over time is referred to as the problem of popularity evolution. Popularity evolution reflects what people focus on and how information flow and diffuse. Popularity evolution prediction of online information helps the studies of information diffusion and human behaviors, assists public opinion monitoring, and brings high application value and commercial value. In recent years, researchers have gained great research achievements. However, there is still a lack of survey which reviews and summarizes existing work. This paper systematically reviews main work of popularity evolution analysis and prediction, and gives summarization to the existing methods and models. First, insight into understanding popularity evolution patterns from qualitative and quantitative perspectives is provided. How to measure factors affecting popularity evolution and to classify them in taxonomy are introduced. Third, the methods of modeling and predicting popularity evolution are categorized into three classes: previous-popularity-based, factor-based, and diffusion-based. These three classes from the following aspects are elaborated: theory, representative work, characteristic comparison, and application scope. Finally, the paper is concluded and future research directions are given according to existing work and current demands.
胡颖,胡长军,傅树深,黄建一. 流行度演化分析与预测综述[J]. 电子与信息学报, 2017, 39(4): 805-816.
HU Ying, HU Changjun, FU Shushen, HUANG Jianyi. Survey on Popularity Evolution Analysis and Prediction. JEIT, 2017, 39(4): 805-816.
WU F and HUBERMAN B A. Popularity, novelty and attention[C]. Proceedings of the 9th ACM Conference on Electronic Commerce, Chicago, 2008: 240-245. doi: 10.1145/ 1386790.1386828.
[2]
WU F and HUBERMAN B A. Novelty and collective attention[J]. Proceedings of the National Academy of Sciences, 2007, 104(45): 17599-17601. doi: 10.1073/pnas.0704916104.
[3]
HONG L, DAN O, and Davison B D. Predicting popular messages in twitter[C]. Proceedings of the 20th International Conference Companion on World Wide Web, Hyderabad, 2011: 57-58. doi: 10.1145/1963192.1963222.
[4]
YANG J and LESKOVEC J. Patterns of temporal variation in online media[C]. Proceedings of the 4th ACM International Conference on Web Search and Data Mining, Hong Kong, 2011: 177-186. doi: 10.1145/1935826.1935863.
WU Xindong, LI Yi, and LI Lei. Influence analysis of online social networks[J]. Chinese Journal of Computers, 2014, 37(4): 735-751.
[6]
KEMPE D, KLEINBERG J, and TARDOSÉ. Maximizing the spread of influence through a social network[C]. Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington DC, 2003: 137-146. doi: 10.1145/956750.956769.
[7]
LERMAN K. Social information processing in news aggregation[J]. IEEE Internet Computing, 2007, 11(6): 16-28. doi 10.1109/mic.2007.136.
[8]
BORGHOL Y, ARDON S, CARLSSON N, et al. The untold story of the clones: content-agnostic factors that impact YouTube video popularity[C]. Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, 2012: 1186-1194. doi 10.1145/ 2339530.2339717.
[9]
KONG S, MEI Q, FENG L, et al. Predicting bursts and popularity of hashtags in real-time[C]. Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval, Gold Coast, 2014: 927-930. doi: 10.1145/2600428.2609476.
[10]
HE X, GAO M, KAN M Y, et al. Predicting the popularity of Web 2.0 items based on user comments[C]. Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval, Gold Coast, 2014: 233-242. doi 10.1145/2600428.2609558.
[11]
SZABO G and HUBERMAN B A. Predicting the popularity of online content[J]. Communications of the ACM, 2010, 53(8): 80-88. doi: 10.1145/1787234.1787254.
[12]
AGARWAL N, LIU H, TANG L, et al. Identifying the influential bloggers in a community[C]. Proceedings of the 2008 International Conference on Web Search and Data Mining, Palo Alto, 2008: 207-218. doi: 10.1145/1341531. 1341559.
[13]
BANDARI R, ASUR S, and HUBERMAN B A. The pulse of news in social media: Forecasting popularity[C]. Proceedings of the 6th International AAAI Conference on Web and Social Media, Dublin, 2012: 26-33.
[14]
CHATZOPOULOU G, SHENG C, and FALOUTSOS M. A first step towards understanding popularity in YouTube[C]. INFOCOM IEEE Conference on Computer Communications Workshops, San Diego, 2010: 1-6. doi 10.1109/infcomw. 2010.5466701.
[15]
ROY S D, MEI T, ZENG W, et al. Towards cross-domain learning for social video popularity prediction[J]. IEEE Transactions on Multimedia, 2013, 15(6): 1255-1267. doi 10.1109/tmm.2013.2265079.
[16]
JAMALI S and RANGWALA H. Digging Digg: Comment mining, popularity prediction, and social network analysis[C]. IEEE International Conference on Web Information Systems and Mining, Shanghai, 2009: 32-38. doi 10.1109/wism. 2009.15.
[17]
YIN P, LUO P, WANG M, et al. A straw shows which way the wind blows: ranking potentially popular items from early votes[C]. Proceedings of the 5th ACM International Conference on Web Search and Data Mining, Seattle, 2012: 623-632. doi: 10.1145/2124295.2124370.
[18]
CHA M, KWAK H, RODRIGUEZ P, et al. I tube, you tube, everybody tubes: Analyzing the world,s largest user generated content video system[C]. Proceedings of the 7th ACM SIGCOMM Conference on Internet Measurement, New York, 2007: 1-14. doi: 10.1145/1298306.1298309.
[19]
CRANE R and SORNETTE D. Robust dynamic classes revealed by measuring the response function of a social system[J]. Proceedings of the National Academy of Sciences, 2008, 105(41): 15649-15653. doi: 10.1073/pnas.0803685105.
[20]
CRANE R and SORNETTE D. Viral, quality, junk videos on YouTube: Separating content from noise in an information- rich environment[C]. AAAI Spring Symposium 2008: Social Information Processing, Stanford, 2008: 18-20.
[21]
FIGUEIREDO F. On the prediction of popularity of trends and hits for user generated videos[C]. Proceedings of the 6th ACM International Conference on Web Search and Data Mining, San Francisco, 2013: 741-746. doi: 10.1145/2433396. 2433489.
[22]
ASUR S, HUBERMAN B A, SZABO G, et al. Trends in social media: Persistence and decay[OL]. Available at SSRN 1755748, 2011. doi: 10.2139/ssrn.1755748.
[23]
FIGUEIREDO F, BENEVENUTO F, and ALMEIDA J M. The tube over time: Characterizing popularity growth of YouTube videos[C]. Proceedings of the 4th ACM International Conference on Web Search and Data Mining, Hong Kong, 2011: 745-754. doi: 10.1145/1935826.1935925.
[24]
CHENG J, ADAMIC L A, KLEINBERG J M, et al. Do cascades recur?[C]. Proceedings of the 25th International Conference on World Wide Web. Montreal, 2016: 671-681. doi: 10.1145/2872427.2882993.
[25]
MATSUBARA Y, SAKURAI Y, PRAKASH B A, et al. Rise and fall patterns of information diffusion: Model and implications[C]. Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, 2012: 6-14. doi: 10.1145/2339530.2339537.
[26]
YU H, XIE L, and SANNER S. The lifecycle of a YouTube video: Phases, content and popularity[C]. 9th International AAAI Conference on Web and Social Media, Oxford, 2015.
[27]
SALGANIK M J, DODDS P S, and WATTS D J. Experimental study of inequality and unpredictability in an artificial cultural market[J]. Science, 2006, 311(5762): 854-856. doi: 10.1126/science.1121066.
[28]
LERMAN K and GALSTYAN A. Analysis of social voting patterns on digg[C]. Proceedings of the First Workshop on Online Social Networks, Seattle, 2008: 7-12. doi: 10.1145/ 1397735.1397738.
[29]
CHANG B, ZHU H, GE Y, et al. Predicting the popularity of online serials with autoregressive models[C]. Proceedings of the 23rd ACM International Conference on Information and Knowledge Management, Shanghai, 2014: 1339-1348. doi: 10.1145/2661829.2662055.
[30]
PINTO H, ALMEIDA J M, and GONCALVES M A. Using early view patterns to predict the popularity of YouTube videos[C]. Proceedings of the 6th ACM International Conference on Web Search and Data Mining, San Francisco, 2013: 365-374. doi: 10.1145/2433396.2433443.
[31]
TAN Z, WANG Y, ZHANG Y, et al. A novel time series approach for predicting the long-term popularity of online videos[J]. IEEE Transactions on Broadcasting, 2016, 62(2): 436-445. doi: 10.1109/TBC.2016.2540522.
[32]
WU J, ZHOU Y, CHIU D M, et al. Modeling dynamics of online video popularity[J]. IEEE Transactions on Multimedia, 2016, 18(9): 1882-1895. doi: 10.1109/TMM.2016.2579600.
[33]
LI H, MA X, WANG F, et al. On popularity prediction of videos shared in online social networks[C]. Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, San Francisco, 2013: 169-178. doi: 10.1145/2505515.2505523.
[34]
TATAR A, LEGUAY J, ANTONIADIS P, et al. Predicting the popularity of online articles based on user comments[C]. Proceedings of the International Conference on Web Intelligence, Mining and Semantics, Sogndal, 2011: 1-8. doi: 10.1145/1988688.1988766.
[35]
SIERSDORFER S, CHELARU S, NEJDL W, et al. How useful are your comments?: Analyzing and predicting YouTube comments and comment ratings[C]. Proceedings of the 19th International Conference on World Wide Web, Raleigh, 2010: 891-900. doi: 10.1145/1772690.1772781.
[36]
HE X, GAO M, KAN M Y, et al. Predicting the popularity of web 2.0 items based on user comments[C]. Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval, Gold Coast, 2014: 233-242. doi: 10.1145/2600428.2609558.
[37]
MA Z, SUN A, and CONG G. On predicting the popularity of newly emerging hashtags in twitter[J]. Journal of the American Society for Information Science and Technology, 2013, 64(7): 1399-1410. doi: 10.1002/asi.22844.
[38]
KHOSLA A, DAS SARMA A, and HAMID R. What makes an image popular?[C]. Proceedings of the 23rd International Conference on World Wide Web, Seoul, 2014: 867-876. doi 10.1145/2566486.2567996.
[39]
BAO P, SHEN H W, HUANG J, et al. Popularity prediction in microblogging network: A case study on sina weibo[C]. Proceedings of the 22nd International Conference on World Wide Web Companion, Rio de Janeiro, 2013: 177-178. doi 10.1145/2487788.2487877.
[40]
LERMAN K and HOGG T. Using a model of social dynamics to predict popularity of news[C]. Proceedings of the 19th International Conference on World Wide Web, Raleigh, 2010: 621-630. doi: 10.1145/1772690.1772754.
[41]
ZHAO Q, ERDOGDU MA, HE HY, et al. SEISMIC: A self-exciting point process model for predicting tweet popularity[C]. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, 2015: 1513-1522. doi: 10.1145/2783258. 2783401.
[42]
LEE J G, MOON S, and SALAMATIAN K. An approach to model and predict the popularity of online contents with explanatory factors[C]. 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, London, 2010, 1: 623-630. doi: 10.1109/WI-IAT.2010.209.
[43]
AHMED M, SPAGNA S, HUICI F, et al. A peek into the future predicting the evolution of popularity in user generated content[C]. Proceedings of the 6th ACM International Conference on Web Search and Data Mining, San Francisco, 2013: 607-616. doi: 10.1145/2433396.2433473.
[44]
FIGUEIREDO F, ALMEIDA J M, GONCALVES M A, et al. TrendLearner: Early prediction of popularity trends of user generated content[J]. Information Sciences, 2016: 349-350, 172-187. doi: 10.1016/j.ins.2016.02.025.
[45]
GRUHL D, GUHA R, LIBEN-NOWELL D, et al. Information diffusion through blogspace[C]. Proceedings of the 13th International Conference on World Wide Web, New York, 2004: 491-501. doi: 10.1145/988672.988739.
[46]
YANG J and LESKOVEC J. Modeling information diffusion in implicit networks[C]. IEEE 10th International Conference on Data Mining, Sydney, 2010: 599-608. doi: 10.1109/icdm. 2010.22.
[47]
ZHAO J, WU J, FENG X, et al. Information propagation in online social networks: A tie-strength perspective[J]. Knowledge and Information Systems, 2012, 32(3): 589-608. doi: 10.1007/s10115-011-0445-x.
[48]
CHENG J, ADAMIC L, DOW P, et al. Can cascades be predicted?[C]. Proceedings of the 23rd International Conference on World Wide Web, Seoul, 2014: 925-936. doi: 10.1145/2566486.2567997.
[49]
KUPAVSKII A, OSTROUMOVA L, UMNOV A, et al. Prediction of retweet cascade size over time[C]. Proceedings of the 21st ACM International Conference on Information and Knowledge Management, Sheraton, 2012: 2335-2338. doi: 10.1145/2396761.2398634.
[50]
ARDON S, BAGCHI A, MAHANTI A, et al. Spatio- temporal and events based analysis of topic popularity in twitter[C]. Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, San Francisco, 2013: 219-228. doi: 10.1145/2505515.2505525.
[51]
WANG S, YAN Z, HU X, et al. Burst time prediction in cascades[C]. 29th AAAI Conference on Artificial Intelligence, Austin, 2015: 325-331.
