Adaptive method for following dynamic topics on twitter

Walid Magdy, Tamer Elsayed

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

16 Citations (Scopus)

Abstract

Many research social studies of public response on social media require following (i.e., tracking) topics on Twitter for long periods of time. The current approaches rely on streaming tweets based on some hashtags or keywords, or following some Twitter accounts. Such approaches lead to limited coverage of on-topic tweets. In this paper, we introduce a novel technique for following such topics in a more effective way. A topic is defined as a set of wellprepared queries that cover the static side of the topic. We propose an automatic approach that adapts to emerging aspects of a tracked broad topic over time. We tested our tracking approach on three broad dynamic topics that are hot in different categories: Egyptian politics, Syrian conflict, and international sports. We measured the effectiveness of our approach over four full days spanning a period of four months to ensure consistency in effectiveness. Experimental results showed that, on average, our approach achieved over 100% increase in recall relative to the baseline Boolean approach, while maintaining an acceptable precision of 83%.

Original languageEnglish
Title of host publicationProceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014
PublisherThe AAAI Press
Pages335-345
Number of pages11
ISBN (Print)9781577356578
Publication statusPublished - 1 Jan 2014
Event8th International Conference on Weblogs and Social Media, ICWSM 2014 - Ann Arbor, United States
Duration: 1 Jun 20144 Jun 2014

Other

Other8th International Conference on Weblogs and Social Media, ICWSM 2014
CountryUnited States
CityAnn Arbor
Period1/6/144/6/14

Fingerprint

Sports

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Magdy, W., & Elsayed, T. (2014). Adaptive method for following dynamic topics on twitter. In Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014 (pp. 335-345). The AAAI Press.

Adaptive method for following dynamic topics on twitter. / Magdy, Walid; Elsayed, Tamer.

Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014. The AAAI Press, 2014. p. 335-345.

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

Magdy, W & Elsayed, T 2014, Adaptive method for following dynamic topics on twitter. in Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014. The AAAI Press, pp. 335-345, 8th International Conference on Weblogs and Social Media, ICWSM 2014, Ann Arbor, United States, 1/6/14.
Magdy W, Elsayed T. Adaptive method for following dynamic topics on twitter. In Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014. The AAAI Press. 2014. p. 335-345
Magdy, Walid ; Elsayed, Tamer. / Adaptive method for following dynamic topics on twitter. Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014. The AAAI Press, 2014. pp. 335-345
@inproceedings{b43e76bdf8c04568ad5c663bd42f54aa,
title = "Adaptive method for following dynamic topics on twitter",
abstract = "Many research social studies of public response on social media require following (i.e., tracking) topics on Twitter for long periods of time. The current approaches rely on streaming tweets based on some hashtags or keywords, or following some Twitter accounts. Such approaches lead to limited coverage of on-topic tweets. In this paper, we introduce a novel technique for following such topics in a more effective way. A topic is defined as a set of wellprepared queries that cover the static side of the topic. We propose an automatic approach that adapts to emerging aspects of a tracked broad topic over time. We tested our tracking approach on three broad dynamic topics that are hot in different categories: Egyptian politics, Syrian conflict, and international sports. We measured the effectiveness of our approach over four full days spanning a period of four months to ensure consistency in effectiveness. Experimental results showed that, on average, our approach achieved over 100{\%} increase in recall relative to the baseline Boolean approach, while maintaining an acceptable precision of 83{\%}.",
author = "Walid Magdy and Tamer Elsayed",
year = "2014",
month = "1",
day = "1",
language = "English",
isbn = "9781577356578",
pages = "335--345",
booktitle = "Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014",
publisher = "The AAAI Press",

}

TY - GEN

T1 - Adaptive method for following dynamic topics on twitter

AU - Magdy, Walid

AU - Elsayed, Tamer

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Many research social studies of public response on social media require following (i.e., tracking) topics on Twitter for long periods of time. The current approaches rely on streaming tweets based on some hashtags or keywords, or following some Twitter accounts. Such approaches lead to limited coverage of on-topic tweets. In this paper, we introduce a novel technique for following such topics in a more effective way. A topic is defined as a set of wellprepared queries that cover the static side of the topic. We propose an automatic approach that adapts to emerging aspects of a tracked broad topic over time. We tested our tracking approach on three broad dynamic topics that are hot in different categories: Egyptian politics, Syrian conflict, and international sports. We measured the effectiveness of our approach over four full days spanning a period of four months to ensure consistency in effectiveness. Experimental results showed that, on average, our approach achieved over 100% increase in recall relative to the baseline Boolean approach, while maintaining an acceptable precision of 83%.

AB - Many research social studies of public response on social media require following (i.e., tracking) topics on Twitter for long periods of time. The current approaches rely on streaming tweets based on some hashtags or keywords, or following some Twitter accounts. Such approaches lead to limited coverage of on-topic tweets. In this paper, we introduce a novel technique for following such topics in a more effective way. A topic is defined as a set of wellprepared queries that cover the static side of the topic. We propose an automatic approach that adapts to emerging aspects of a tracked broad topic over time. We tested our tracking approach on three broad dynamic topics that are hot in different categories: Egyptian politics, Syrian conflict, and international sports. We measured the effectiveness of our approach over four full days spanning a period of four months to ensure consistency in effectiveness. Experimental results showed that, on average, our approach achieved over 100% increase in recall relative to the baseline Boolean approach, while maintaining an acceptable precision of 83%.

UR - http://www.scopus.com/inward/record.url?scp=84909978911&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84909978911&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84909978911

SN - 9781577356578

SP - 335

EP - 345

BT - Proceedings of the 8th International Conference on Weblogs and Social Media, ICWSM 2014

PB - The AAAI Press

ER -