A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Non-linear Time-series Analysis of Social Influence
2016
Proceedings of the 2016 on SIGMOD'16 PhD Symposium - SIGMOD'16 PhD
In this paper, we present ∆-SPOT, a non-linear model for analysing large scale web search data, and its fitting algorithm. ∆-SPOT can forecast long-range future dynamics of the keywords/queries. We use the Google Search, Twitter and MemeTracker data set for extensive experiments, which show that our method outperforms other non-linear mining methods. We also provide an online algorithm contributing to the need of monitoring multiple co-evolving data sequences.
doi:10.1145/2926693.2929902
dblp:conf/sigmod/Do16
fatcat:mo6ckmlnzrcdfgklewtedxayvi