TENSORCAST: forecasting and mining with coupled tensors

• Type: Article in International Scientific Journal
• Date: 2019

Authors

araujo, mr (Author) FCUP; Pedro Ribeiro (Author) FCUP; Song, HA (Author) Other; Faloutsos, C (Author) Other

Journal

Title: Knowledge and Information Systems

Vol. 59

Pages: 497-522

ISSN: 0219-1377

Publisher: Springer Nature

Indexing

ISI Web of Knowledge - 8 Citations

Scopus - 7 Citations

Other information

Authenticus ID: P-00Q-DCJ

DOI: 10.1007/s10115-018-1223-9

Abstract (EN): Given an heterogeneous social network, can we forecast its future? Can we predict who will start using a given hashtag on twitter? Can we leverage side information, such as who retweets or follows whom, to improve our membership forecasts? We present TENSORCAST, a novel method that forecasts time-evolving networks more accurately than current state-of-the-art methods by incorporating multiple data sources in coupled tensors. TENSORCAST is (a) scalable, being linearithmic on the number of connections; (b) effective, achieving over 20% improved precision on top-1000 forecasts of community members; (c) general, being applicable to data sources with different structure. We run our method on multiple real-world networks, including DBLP, epidemiology data, power grid data, and a Twitter temporal network with over 310 million nonzeros, where we predict the evolution of the activity of the use of political hashtags.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 26