Geoscope

Online detection of geo-correlated information trends in social networks

Ceren Budak, Theodore Georgiou, Divyakant Agrawal, Amr El Abbadi

Research output: Chapter in Book/Report/Conference proceedingChapter

29 Citations (Scopus)

Abstract

The First Law of Geography states "Everything is related to everything else, but near things are more related than distant things". This spatial significance has implications in various applications, trend detection being one of them. In this paper we propose a new algorithmic tool, GeoScope, to detect geo-trends. GeoScope is a data streams solution that detects correlations between topics and locations in a sliding window, in addition to analyzing topics and locations independently. GeoScope offers theoretical guarantees for detecting all trending correlated pairs while requiring only sublinear space and running time. We perform various human validation tasks to demonstrate the value of GeoScope. The results show that human judges prefer GeoScope to the best performing baseline solution 4:1 in terms of the geographical significance of the presented information. As the Twitter analysis demonstrates, Geo- Scope successfully filters out topics without geo-intent and detects various local interests such as emergency events, political demonstrations or cultural events. Experiments on Twitter show that Geo- Scope has perfect recall and near-perfect precision.

Original languageEnglish
Title of host publicationProceedings of the VLDB Endowment
PublisherAssociation for Computing Machinery
Pages229-240
Number of pages12
Volume7
Edition4
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Demonstrations
Experiments

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Computer Science(all)

Cite this

Budak, C., Georgiou, T., Agrawal, D., & El Abbadi, A. (2013). Geoscope: Online detection of geo-correlated information trends in social networks. In Proceedings of the VLDB Endowment (4 ed., Vol. 7, pp. 229-240). Association for Computing Machinery.

Geoscope : Online detection of geo-correlated information trends in social networks. / Budak, Ceren; Georgiou, Theodore; Agrawal, Divyakant; El Abbadi, Amr.

Proceedings of the VLDB Endowment. Vol. 7 4. ed. Association for Computing Machinery, 2013. p. 229-240.

Research output: Chapter in Book/Report/Conference proceedingChapter

Budak, C, Georgiou, T, Agrawal, D & El Abbadi, A 2013, Geoscope: Online detection of geo-correlated information trends in social networks. in Proceedings of the VLDB Endowment. 4 edn, vol. 7, Association for Computing Machinery, pp. 229-240.
Budak C, Georgiou T, Agrawal D, El Abbadi A. Geoscope: Online detection of geo-correlated information trends in social networks. In Proceedings of the VLDB Endowment. 4 ed. Vol. 7. Association for Computing Machinery. 2013. p. 229-240
Budak, Ceren ; Georgiou, Theodore ; Agrawal, Divyakant ; El Abbadi, Amr. / Geoscope : Online detection of geo-correlated information trends in social networks. Proceedings of the VLDB Endowment. Vol. 7 4. ed. Association for Computing Machinery, 2013. pp. 229-240
@inbook{3bec8e31988d4dc38d3e5a25ea7a3ea2,
title = "Geoscope: Online detection of geo-correlated information trends in social networks",
abstract = "The First Law of Geography states {"}Everything is related to everything else, but near things are more related than distant things{"}. This spatial significance has implications in various applications, trend detection being one of them. In this paper we propose a new algorithmic tool, GeoScope, to detect geo-trends. GeoScope is a data streams solution that detects correlations between topics and locations in a sliding window, in addition to analyzing topics and locations independently. GeoScope offers theoretical guarantees for detecting all trending correlated pairs while requiring only sublinear space and running time. We perform various human validation tasks to demonstrate the value of GeoScope. The results show that human judges prefer GeoScope to the best performing baseline solution 4:1 in terms of the geographical significance of the presented information. As the Twitter analysis demonstrates, Geo- Scope successfully filters out topics without geo-intent and detects various local interests such as emergency events, political demonstrations or cultural events. Experiments on Twitter show that Geo- Scope has perfect recall and near-perfect precision.",
author = "Ceren Budak and Theodore Georgiou and Divyakant Agrawal and {El Abbadi}, Amr",
year = "2013",
language = "English",
volume = "7",
pages = "229--240",
booktitle = "Proceedings of the VLDB Endowment",
publisher = "Association for Computing Machinery",
edition = "4",

}

TY - CHAP

T1 - Geoscope

T2 - Online detection of geo-correlated information trends in social networks

AU - Budak, Ceren

AU - Georgiou, Theodore

AU - Agrawal, Divyakant

AU - El Abbadi, Amr

PY - 2013

Y1 - 2013

N2 - The First Law of Geography states "Everything is related to everything else, but near things are more related than distant things". This spatial significance has implications in various applications, trend detection being one of them. In this paper we propose a new algorithmic tool, GeoScope, to detect geo-trends. GeoScope is a data streams solution that detects correlations between topics and locations in a sliding window, in addition to analyzing topics and locations independently. GeoScope offers theoretical guarantees for detecting all trending correlated pairs while requiring only sublinear space and running time. We perform various human validation tasks to demonstrate the value of GeoScope. The results show that human judges prefer GeoScope to the best performing baseline solution 4:1 in terms of the geographical significance of the presented information. As the Twitter analysis demonstrates, Geo- Scope successfully filters out topics without geo-intent and detects various local interests such as emergency events, political demonstrations or cultural events. Experiments on Twitter show that Geo- Scope has perfect recall and near-perfect precision.

AB - The First Law of Geography states "Everything is related to everything else, but near things are more related than distant things". This spatial significance has implications in various applications, trend detection being one of them. In this paper we propose a new algorithmic tool, GeoScope, to detect geo-trends. GeoScope is a data streams solution that detects correlations between topics and locations in a sliding window, in addition to analyzing topics and locations independently. GeoScope offers theoretical guarantees for detecting all trending correlated pairs while requiring only sublinear space and running time. We perform various human validation tasks to demonstrate the value of GeoScope. The results show that human judges prefer GeoScope to the best performing baseline solution 4:1 in terms of the geographical significance of the presented information. As the Twitter analysis demonstrates, Geo- Scope successfully filters out topics without geo-intent and detects various local interests such as emergency events, political demonstrations or cultural events. Experiments on Twitter show that Geo- Scope has perfect recall and near-perfect precision.

UR - http://www.scopus.com/inward/record.url?scp=84896985660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896985660&partnerID=8YFLogxK

M3 - Chapter

VL - 7

SP - 229

EP - 240

BT - Proceedings of the VLDB Endowment

PB - Association for Computing Machinery

ER -