Spatio-Temporal Meme Prediction: Learning What Hashtags Will Be Popular Where Conference Paper

abstract

• In this paper, we tackle the problem of predicting what online memes will be popular in what locations. Specifically, we develop data-driven approaches building on the global footprint of 755 million geo-tagged hashtags spread via Twitter. Our proposed methods model the geo-spatial propagation of online information spread to identify which hashtags will become popular in specific locations. Concretely, we develop a novel reinforcement learning approach that incrementally updates the best geo-spatial model. In experiments, we find that the proposed method outperforms alternative linear regression based methods. Copyright 2013 ACM.

name of conference

• Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13

authors

• Caverlee, James

published proceedings

• PROCEEDINGS OF THE 22ND ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM'13)

author list (cited authors)

• Kamath, K. Y., & Caverlee, J.

citation count

• 12

complete list of authors

• Kamath, Krishna Y||Caverlee, James

editor list (cited editors)

• He, Q. i., Iyengar, A., Nejdl, W., Pei, J., & Rastogi, R.

publication date

• October 2013

publisher

• Association for Computing Machinery (ACM)  Publisher

keywords

• Social Media
• Spatial Impact
• Spatio-temporal Analysis

Digital Object Identifier (DOI)

• 10.1145/2505515.2505579

International Standard Book Number (ISBN) 13

• 9781450322638

start page

• 1341

end page

• 1350

URL

• http://dx.doi.org/10.1145/2505515.2505579