Precocious identification of popular topics on Twitter with the employment of predictive clustering

The present paper outlines a novel approach to predict popularity of topics for social network Twitter; the method is designed to identify precociously the topics able to demonstrate “explosive” growth in popularity. First of all, the predictive clustering method ascertains real (not written in hash-tags!) topics of tweets and then predicts popularity rates for the topics. The same clustering algorithm is employed both to ascertain the real topic of a message and to cluster segments of time series (in order to predict topics popularity), namely, maximum likelihood adaptive neural system based upon modelling field theory. In the course of wide-ranging simulation, typical variants of “pre-explosive” dynamics were revealed; some of them were turned out to be equal to heuristic techniques to predict topics popularity well known for PR community collaborating with the network (“crab,” “Pesavento’s butterfly,” etc.).

[1]  Xin Fu,et al.  Study of collective user behaviour in Twitter: a fuzzy approach , 2014, Neural Computing and Applications.

[2]  Duong Tuan Anh,et al.  Motif-Based Method for Initialization the K-Means Clustering for Time Series Data , 2011, Australasian Conference on Artificial Intelligence.

[3]  Vasilii A. Gromov,et al.  Chaotic time series prediction with employment of ant colony optimization , 2012, Expert Syst. Appl..

[4]  Ying Wah Teh,et al.  Time-series clustering - A decade review , 2015, Inf. Syst..

[5]  Vasilii A. Gromov,et al.  Predictive clustering on non-successive observations for multi-step ahead chaotic time series prediction , 2015, Neural Computing and Applications.

[6]  Saso Dzeroski,et al.  Analysis of Time Series Data with Predictive Clustering Trees , 2006, KDID.

[7]  Roberto V. Zicari,et al.  PoliTwi: Early detection of emerging political topics on twitter and the impact on concept-level sentiment analysis , 2014, Knowl. Based Syst..

[8]  N. Wermuth,et al.  Nonlinear Time Series: Nonparametric and Parametric Methods , 2005 .

[9]  Alicia Troncoso Lora,et al.  Partitioning-Clustering Techniques Applied to the Electricity Price Time Series , 2007, IDEAL.

[10]  Luc De Raedt,et al.  Top-Down Induction of Clustering Trees , 1998, ICML.

[11]  Russel Pears,et al.  Multiple Time-Series Prediction through Multiple Time-Series Relationships Profiling and Clustered Recurring Trends , 2011, PAKDD.

[12]  Nikola K. Kasabov,et al.  Evolving connectionist systems for adaptive learning and knowledge discovery: Trends and directions , 2015, Knowl. Based Syst..

[13]  Felipe Bravo-Marquez,et al.  Meta-level sentiment models for big social data analysis , 2014, Knowl. Based Syst..

[14]  Francisco Martinez Alvarez,et al.  Energy Time Series Forecasting Based on Pattern Sequence Similarity , 2011, IEEE Transactions on Knowledge and Data Engineering.

[15]  Russel Pears,et al.  A Novel Evolving Clustering Algorithm with Polynomial Regression for Chaotic Time-Series Prediction , 2009, ICONIP.

[16]  Bruno S. Silvestre,et al.  Social Media? Get Serious! Understanding the Functional Building Blocks of Social Media , 2011 .

[17]  Witold Pedrycz,et al.  The modeling and prediction of time series based on synergy of high-order fuzzy cognitive map and fuzzy c-means clustering , 2014, Knowl. Based Syst..