Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information

Hancheng Ge, James Caverlee, Nan Zhang, Anna Squicciarini

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

Modeling, understanding, and predicting the spatio-temporal dynamics of online memes are important tasks, with ramifications on location-based services, social media search, targeted advertising and content delivery networks. However, the raw data revealing these dynamics are often incomplete and error-prone; for example, API limitations and data sampling policies can lead to an incomplete (and often biased) perspective on these dynamics. Hence, in this paper, we investigate new methods for uncovering the full (underlying) distribution through a novel spatio-temporal dynamics recovery framework which models the latent relationships among locations, memes, and times. By integrating these hidden relationships into a tensor-based recovery framework - called AirCP - we find that high-quality models of meme spread can be built with access to only a fraction of the full data. Experimental results on both synthetic and real-world Twitter hashtag data demonstrate the promising performance of the proposed framework: an average improvement of over 27% in recovering the spatio-temporal dynamics of hashtags versus five state-of-the-art alternatives.

Original languageEnglish (US)
Title of host publicationCIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages1493-1502
Number of pages10
ISBN (Electronic)9781450340731
DOIs
StatePublished - Oct 24 2016
Event25th ACM International Conference on Information and Knowledge Management, CIKM 2016 - Indianapolis, United States
Duration: Oct 24 2016Oct 28 2016

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings
Volume24-28-October-2016

Other

Other25th ACM International Conference on Information and Knowledge Management, CIKM 2016
CountryUnited States
CityIndianapolis
Period10/24/1610/28/16

Fingerprint

Incomplete information
Search advertising
Sampling
Location-based services
Modeling
Twitter
Social media

All Science Journal Classification (ASJC) codes

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Ge, H., Caverlee, J., Zhang, N., & Squicciarini, A. (2016). Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management (pp. 1493-1502). (International Conference on Information and Knowledge Management, Proceedings; Vol. 24-28-October-2016). Association for Computing Machinery. https://doi.org/10.1145/2983323.2983782
Ge, Hancheng ; Caverlee, James ; Zhang, Nan ; Squicciarini, Anna. / Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information. CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery, 2016. pp. 1493-1502 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{0816e1c9c13442c5af36fbac1129a869,
title = "Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information",
abstract = "Modeling, understanding, and predicting the spatio-temporal dynamics of online memes are important tasks, with ramifications on location-based services, social media search, targeted advertising and content delivery networks. However, the raw data revealing these dynamics are often incomplete and error-prone; for example, API limitations and data sampling policies can lead to an incomplete (and often biased) perspective on these dynamics. Hence, in this paper, we investigate new methods for uncovering the full (underlying) distribution through a novel spatio-temporal dynamics recovery framework which models the latent relationships among locations, memes, and times. By integrating these hidden relationships into a tensor-based recovery framework - called AirCP - we find that high-quality models of meme spread can be built with access to only a fraction of the full data. Experimental results on both synthetic and real-world Twitter hashtag data demonstrate the promising performance of the proposed framework: an average improvement of over 27{\%} in recovering the spatio-temporal dynamics of hashtags versus five state-of-the-art alternatives.",
author = "Hancheng Ge and James Caverlee and Nan Zhang and Anna Squicciarini",
year = "2016",
month = "10",
day = "24",
doi = "10.1145/2983323.2983782",
language = "English (US)",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "1493--1502",
booktitle = "CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management",

}

Ge, H, Caverlee, J, Zhang, N & Squicciarini, A 2016, Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information. in CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, vol. 24-28-October-2016, Association for Computing Machinery, pp. 1493-1502, 25th ACM International Conference on Information and Knowledge Management, CIKM 2016, Indianapolis, United States, 10/24/16. https://doi.org/10.1145/2983323.2983782

Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information. / Ge, Hancheng; Caverlee, James; Zhang, Nan; Squicciarini, Anna.

CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery, 2016. p. 1493-1502 (International Conference on Information and Knowledge Management, Proceedings; Vol. 24-28-October-2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information

AU - Ge, Hancheng

AU - Caverlee, James

AU - Zhang, Nan

AU - Squicciarini, Anna

PY - 2016/10/24

Y1 - 2016/10/24

N2 - Modeling, understanding, and predicting the spatio-temporal dynamics of online memes are important tasks, with ramifications on location-based services, social media search, targeted advertising and content delivery networks. However, the raw data revealing these dynamics are often incomplete and error-prone; for example, API limitations and data sampling policies can lead to an incomplete (and often biased) perspective on these dynamics. Hence, in this paper, we investigate new methods for uncovering the full (underlying) distribution through a novel spatio-temporal dynamics recovery framework which models the latent relationships among locations, memes, and times. By integrating these hidden relationships into a tensor-based recovery framework - called AirCP - we find that high-quality models of meme spread can be built with access to only a fraction of the full data. Experimental results on both synthetic and real-world Twitter hashtag data demonstrate the promising performance of the proposed framework: an average improvement of over 27% in recovering the spatio-temporal dynamics of hashtags versus five state-of-the-art alternatives.

AB - Modeling, understanding, and predicting the spatio-temporal dynamics of online memes are important tasks, with ramifications on location-based services, social media search, targeted advertising and content delivery networks. However, the raw data revealing these dynamics are often incomplete and error-prone; for example, API limitations and data sampling policies can lead to an incomplete (and often biased) perspective on these dynamics. Hence, in this paper, we investigate new methods for uncovering the full (underlying) distribution through a novel spatio-temporal dynamics recovery framework which models the latent relationships among locations, memes, and times. By integrating these hidden relationships into a tensor-based recovery framework - called AirCP - we find that high-quality models of meme spread can be built with access to only a fraction of the full data. Experimental results on both synthetic and real-world Twitter hashtag data demonstrate the promising performance of the proposed framework: an average improvement of over 27% in recovering the spatio-temporal dynamics of hashtags versus five state-of-the-art alternatives.

UR - http://www.scopus.com/inward/record.url?scp=84996503330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996503330&partnerID=8YFLogxK

U2 - 10.1145/2983323.2983782

DO - 10.1145/2983323.2983782

M3 - Conference contribution

AN - SCOPUS:84996503330

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 1493

EP - 1502

BT - CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery

ER -

Ge H, Caverlee J, Zhang N, Squicciarini A. Uncovering the spatio-temporal dynamics of memes in the presence of incomplete information. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery. 2016. p. 1493-1502. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2983323.2983782