CROP: An Efficient Cross-Platform Event Popularity Prediction Model for Online Media

The popularity analysis of social media is crucial for monitoring the spread of information, which is beneficial to public concerns track and decision-making for online platforms. Numerous studies concentrate on the trend analysis on single platform, but they neglect the data correlation between different platforms. In this paper, we propose CROP, a cross-platform event popularity prediction model to forecast the popularity of events on one platform based on the information of the auxiliary platform. We first define the cross-platform event popularity prediction problem. Then we clean the data and explore the slot matching of event time series in diverse platforms. Moreover, we first define the aggregated popularity for the feature construction of event popularity prediction model. Finally, extensive experiments based on events data show that CROP achieves great improvement for predicting accuracy over other baseline approaches.

[1]  Hans-Peter Kriegel,et al.  SigniTrend: scalable detection of emerging topics in textual streams by hashed significance thresholds , 2014, KDD.

[2]  Jie Zhao,et al.  A Fine-Grained Approach for Extracting Events on Microblogs , 2014, DEXA.

[3]  Jure Leskovec,et al.  Patterns of temporal variation in online media , 2011, WSDM '11.

[4]  Salvatore Orlando,et al.  A Study on Microblog and Search Engine User Behaviors: How Twitter Trending Topics Help Predict Google Hot Queries , 2013 .

[5]  Eamonn J. Keogh,et al.  Derivative Dynamic Time Warping , 2001, SDM.

[6]  Yutaka Matsuo,et al.  Earthquake shakes Twitter users: real-time event detection by social sensors , 2010, WWW '10.

[7]  R. Leipus,et al.  Rescaled variance and related tests for long memory in volatility and levels , 2003 .

[8]  Bernardo A. Huberman,et al.  The Pulse of News in Social Media: Forecasting Popularity , 2012, ICWSM.

[9]  Guihai Chen,et al.  DancingLines: An Analytical Scheme to Depict Cross-Platform Event Popularity , 2017, DEXA.

[10]  Nick Koudas,et al.  TwitterMonitor: trend detection over the twitter stream , 2010, SIGMOD Conference.

[11]  Biao Wang,et al.  CPB: a classification-based approach for burst time prediction in cascades , 2015, Knowledge and Information Systems.

[12]  Imed Kacem,et al.  Modeling Information Diffusion via Reputation Estimation , 2016, DEXA.

[13]  Yan Tang,et al.  ESAP: A Novel Approach for Cross-Platform Event Dissemination Trend Analysis Between Social Network and Search Engine , 2016, WISE.

[14]  Salvatore Orlando,et al.  Twitter anticipates bursts of requests for Wikipedia articles , 2013, DUBMOD '13.

[15]  W. Art Chaovalitwongse,et al.  An Efficient Time Series Subsequence Pattern Mining and Prediction Framework with an Application to Respiratory Motion Prediction , 2016, AAAI.

[16]  Aristides Gionis,et al.  Event detection in activity networks , 2014, KDD.

[17]  Naren Ramakrishnan,et al.  Predicting the Popularity of News Articles , 2016, SDM.

[18]  Kai Chen,et al.  Cost-Effective Online Trending Topic Detection and Popularity Prediction in Microblogging , 2016, ACM Trans. Inf. Syst..

[19]  Salvatore Orlando,et al.  Trending Topics on Twitter Improve the Prediction of Google Hot Queries , 2013, 2013 International Conference on Social Computing.

[20]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[21]  Zhenchang Xing,et al.  Towards Correlating Search on Google and Asking on Stack Overflow , 2016, 2016 IEEE 40th Annual Computer Software and Applications Conference (COMPSAC).

[22]  Jure Leskovec,et al.  Meme-tracking and the dynamics of the news cycle , 2009, KDD.

[23]  Viktor K. Prasanna,et al.  Event Extraction from Unstructured Text Data , 2015, DEXA.

[24]  Zbigniew R. Struzik,et al.  The Haar Wavelet Transform in the Time Series Similarity Paradigm , 1999, PKDD.