On predicting Twitter trend

Factors and models

Peng Zhang, Xufei Wang, Baoxin Li

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

6 Citations (Scopus)

Abstract

In this paper, we predict hashtag trend in Twitter network with two basic issues under investigation, i.e. trend factors and prediction models. To address the first issue, we consider different content and context factors by designing features from tweet messages, network topology, user behavior, etc. To address the second issue, we adopt prediction models that have different combinations of the two basic model properties, i.e. linearity and state-space. Experiments on large Twitter dataset show that both content and context factors can help trend prediction. However, the most relevant factors are derived from user behaviors on the specific trend. Non-linear models are significantly better than their linear counterparts, which can be further slightly improved by the adoption of state-space models.

Original languageEnglish (US)
Title of host publicationProceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013
PublisherAssociation for Computing Machinery
Pages1427-1429
Number of pages3
ISBN (Print)9781450322409
DOIs
StatePublished - 2013
Event2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013 - Niagara Falls, ON, Canada
Duration: Aug 25 2013Aug 28 2013

Other

Other2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013
CountryCanada
CityNiagara Falls, ON
Period8/25/138/28/13

Fingerprint

Topology
Experiments

Keywords

  • Information diffusion
  • Trend prediction
  • Twitter

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Zhang, P., Wang, X., & Li, B. (2013). On predicting Twitter trend: Factors and models. In Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013 (pp. 1427-1429). Association for Computing Machinery. https://doi.org/10.1145/2492517.2492576

On predicting Twitter trend : Factors and models. / Zhang, Peng; Wang, Xufei; Li, Baoxin.

Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013. Association for Computing Machinery, 2013. p. 1427-1429.

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

Zhang, P, Wang, X & Li, B 2013, On predicting Twitter trend: Factors and models. in Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013. Association for Computing Machinery, pp. 1427-1429, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013, Niagara Falls, ON, Canada, 8/25/13. https://doi.org/10.1145/2492517.2492576
Zhang P, Wang X, Li B. On predicting Twitter trend: Factors and models. In Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013. Association for Computing Machinery. 2013. p. 1427-1429 https://doi.org/10.1145/2492517.2492576
Zhang, Peng ; Wang, Xufei ; Li, Baoxin. / On predicting Twitter trend : Factors and models. Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013. Association for Computing Machinery, 2013. pp. 1427-1429
@inproceedings{f193d05792ab4237a36808111a048164,
title = "On predicting Twitter trend: Factors and models",
abstract = "In this paper, we predict hashtag trend in Twitter network with two basic issues under investigation, i.e. trend factors and prediction models. To address the first issue, we consider different content and context factors by designing features from tweet messages, network topology, user behavior, etc. To address the second issue, we adopt prediction models that have different combinations of the two basic model properties, i.e. linearity and state-space. Experiments on large Twitter dataset show that both content and context factors can help trend prediction. However, the most relevant factors are derived from user behaviors on the specific trend. Non-linear models are significantly better than their linear counterparts, which can be further slightly improved by the adoption of state-space models.",
keywords = "Information diffusion, Trend prediction, Twitter",
author = "Peng Zhang and Xufei Wang and Baoxin Li",
year = "2013",
doi = "10.1145/2492517.2492576",
language = "English (US)",
isbn = "9781450322409",
pages = "1427--1429",
booktitle = "Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - On predicting Twitter trend

T2 - Factors and models

AU - Zhang, Peng

AU - Wang, Xufei

AU - Li, Baoxin

PY - 2013

Y1 - 2013

N2 - In this paper, we predict hashtag trend in Twitter network with two basic issues under investigation, i.e. trend factors and prediction models. To address the first issue, we consider different content and context factors by designing features from tweet messages, network topology, user behavior, etc. To address the second issue, we adopt prediction models that have different combinations of the two basic model properties, i.e. linearity and state-space. Experiments on large Twitter dataset show that both content and context factors can help trend prediction. However, the most relevant factors are derived from user behaviors on the specific trend. Non-linear models are significantly better than their linear counterparts, which can be further slightly improved by the adoption of state-space models.

AB - In this paper, we predict hashtag trend in Twitter network with two basic issues under investigation, i.e. trend factors and prediction models. To address the first issue, we consider different content and context factors by designing features from tweet messages, network topology, user behavior, etc. To address the second issue, we adopt prediction models that have different combinations of the two basic model properties, i.e. linearity and state-space. Experiments on large Twitter dataset show that both content and context factors can help trend prediction. However, the most relevant factors are derived from user behaviors on the specific trend. Non-linear models are significantly better than their linear counterparts, which can be further slightly improved by the adoption of state-space models.

KW - Information diffusion

KW - Trend prediction

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84893260877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893260877&partnerID=8YFLogxK

U2 - 10.1145/2492517.2492576

DO - 10.1145/2492517.2492576

M3 - Conference contribution

SN - 9781450322409

SP - 1427

EP - 1429

BT - Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2013

PB - Association for Computing Machinery

ER -