RetweetPatterns: Detection of Spatio-Temporal Patterns of Retweets

Abstract : Social media is strongly present in people's everyday life and Twitter is one example that stands out. The data within these types of services can be analyzed in order to discover useful knowledge. One interesting approach is to use data mining techniques to perceive hidden behaviours and patterns. The primary focus of this paper is the identification of patterns of retweets and to understand how information spreads over time in Twitter. The aim of this work lies in the adaptation of the GetMove tool, that is capable of extracting spatio-temporal pattern tra-jectories, and TweeProfiles, that identifies tweet profiles regarding several dimensions: spatial, temporal, social and content. We hope that the more flexible clustering strategy from TweeProfiles will enhance the results extracted by GetMove. We study the application of said mechanism to one case study and developed a visualization tool to interpret the results.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01362428
Contributor : Pascal Poncelet <>
Submitted on : Thursday, September 8, 2016 - 5:11:10 PM
Last modification on : Friday, March 29, 2019 - 9:12:06 AM
Long-term archiving on : Friday, December 9, 2016 - 1:32:22 PM

File

WorldCist2016.pdf
Files produced by the author(s)

Identifiers

Citation

Tomy Rodrigues, Tiago Cunha, Dino Ienco, Pascal Poncelet, Carlos Soares. RetweetPatterns: Detection of Spatio-Temporal Patterns of Retweets. WorldCIST: World Conference on Information Systems and Technologies, Mar 2016, Recife, Brazil. pp.879-888, ⟨10.1007/978-3-319-31232-3_83⟩. ⟨lirmm-01362428⟩

Share

Metrics

Record views

486

Files downloads

401