Abstract

The explosive growth of social media sites brings about massive amounts of high-dimensional data. Feature selection is effective in preparing high-dimensional data for data analytics. The characteristics of social media present novel challenges for feature selection. First, social media data is not fully structured and its features are usually not predefined, but are generated dynamically. For example, in Twitter, slang words (features) are created everyday and quickly become popular within a short period of time. It is hard to directly apply traditional batch-mode feature selection methods to find such features. Second, given the nature of social media, label information is costly to collect. It exacerbates the problem of feature selection without knowing feature relevance. On the other hand, opportunities are also unequivocally present with additional data sources; for example, link information is ubiquitous in social media and could be helpful in selecting relevant features. In this paper, we study a novel problem to conduct unsupervised streaming feature selection for social media data. We investigate how to exploit link information in streaming feature selection, resulting in a novel unsupervised streaming feature selection framework USFS. Experimental results on two real-world social media datasets show the effectiveness and efficiency of the proposed framework comparing with the state-of-the-art unsupervised feature selection algorithms.

Original languageEnglish (US)
Title of host publicationInternational Conference on Information and Knowledge Management, Proceedings
PublisherAssociation for Computing Machinery
Pages1041-1050
Number of pages10
Volume19-23-Oct-2015
ISBN (Print)9781450337946
DOIs
StatePublished - Oct 17 2015
Event24th ACM International Conference on Information and Knowledge Management, CIKM 2015 - Melbourne, Australia
Duration: Oct 19 2015Oct 23 2015

Other

Other24th ACM International Conference on Information and Knowledge Management, CIKM 2015
CountryAustralia
CityMelbourne
Period10/19/1510/23/15

Fingerprint

Social media
Feature selection
Twitter
Data sources
Batch

Keywords

  • Social media data
  • Streaming features
  • Unsupervised feature selection

ASJC Scopus subject areas

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

Cite this

Li, J., Hu, X., Tang, J., & Liu, H. (2015). Unsupervised streaming feature selection in social media. In International Conference on Information and Knowledge Management, Proceedings (Vol. 19-23-Oct-2015, pp. 1041-1050). Association for Computing Machinery. https://doi.org/10.1145/2806416.2806501

Unsupervised streaming feature selection in social media. / Li, Jundong; Hu, Xia; Tang, Jiliang; Liu, Huan.

International Conference on Information and Knowledge Management, Proceedings. Vol. 19-23-Oct-2015 Association for Computing Machinery, 2015. p. 1041-1050.

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

Li, J, Hu, X, Tang, J & Liu, H 2015, Unsupervised streaming feature selection in social media. in International Conference on Information and Knowledge Management, Proceedings. vol. 19-23-Oct-2015, Association for Computing Machinery, pp. 1041-1050, 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourne, Australia, 10/19/15. https://doi.org/10.1145/2806416.2806501
Li J, Hu X, Tang J, Liu H. Unsupervised streaming feature selection in social media. In International Conference on Information and Knowledge Management, Proceedings. Vol. 19-23-Oct-2015. Association for Computing Machinery. 2015. p. 1041-1050 https://doi.org/10.1145/2806416.2806501
Li, Jundong ; Hu, Xia ; Tang, Jiliang ; Liu, Huan. / Unsupervised streaming feature selection in social media. International Conference on Information and Knowledge Management, Proceedings. Vol. 19-23-Oct-2015 Association for Computing Machinery, 2015. pp. 1041-1050
@inproceedings{fdbb2ca2a23044bf91c17b55cc7f56f3,
title = "Unsupervised streaming feature selection in social media",
abstract = "The explosive growth of social media sites brings about massive amounts of high-dimensional data. Feature selection is effective in preparing high-dimensional data for data analytics. The characteristics of social media present novel challenges for feature selection. First, social media data is not fully structured and its features are usually not predefined, but are generated dynamically. For example, in Twitter, slang words (features) are created everyday and quickly become popular within a short period of time. It is hard to directly apply traditional batch-mode feature selection methods to find such features. Second, given the nature of social media, label information is costly to collect. It exacerbates the problem of feature selection without knowing feature relevance. On the other hand, opportunities are also unequivocally present with additional data sources; for example, link information is ubiquitous in social media and could be helpful in selecting relevant features. In this paper, we study a novel problem to conduct unsupervised streaming feature selection for social media data. We investigate how to exploit link information in streaming feature selection, resulting in a novel unsupervised streaming feature selection framework USFS. Experimental results on two real-world social media datasets show the effectiveness and efficiency of the proposed framework comparing with the state-of-the-art unsupervised feature selection algorithms.",
keywords = "Social media data, Streaming features, Unsupervised feature selection",
author = "Jundong Li and Xia Hu and Jiliang Tang and Huan Liu",
year = "2015",
month = "10",
day = "17",
doi = "10.1145/2806416.2806501",
language = "English (US)",
isbn = "9781450337946",
volume = "19-23-Oct-2015",
pages = "1041--1050",
booktitle = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Unsupervised streaming feature selection in social media

AU - Li, Jundong

AU - Hu, Xia

AU - Tang, Jiliang

AU - Liu, Huan

PY - 2015/10/17

Y1 - 2015/10/17

N2 - The explosive growth of social media sites brings about massive amounts of high-dimensional data. Feature selection is effective in preparing high-dimensional data for data analytics. The characteristics of social media present novel challenges for feature selection. First, social media data is not fully structured and its features are usually not predefined, but are generated dynamically. For example, in Twitter, slang words (features) are created everyday and quickly become popular within a short period of time. It is hard to directly apply traditional batch-mode feature selection methods to find such features. Second, given the nature of social media, label information is costly to collect. It exacerbates the problem of feature selection without knowing feature relevance. On the other hand, opportunities are also unequivocally present with additional data sources; for example, link information is ubiquitous in social media and could be helpful in selecting relevant features. In this paper, we study a novel problem to conduct unsupervised streaming feature selection for social media data. We investigate how to exploit link information in streaming feature selection, resulting in a novel unsupervised streaming feature selection framework USFS. Experimental results on two real-world social media datasets show the effectiveness and efficiency of the proposed framework comparing with the state-of-the-art unsupervised feature selection algorithms.

AB - The explosive growth of social media sites brings about massive amounts of high-dimensional data. Feature selection is effective in preparing high-dimensional data for data analytics. The characteristics of social media present novel challenges for feature selection. First, social media data is not fully structured and its features are usually not predefined, but are generated dynamically. For example, in Twitter, slang words (features) are created everyday and quickly become popular within a short period of time. It is hard to directly apply traditional batch-mode feature selection methods to find such features. Second, given the nature of social media, label information is costly to collect. It exacerbates the problem of feature selection without knowing feature relevance. On the other hand, opportunities are also unequivocally present with additional data sources; for example, link information is ubiquitous in social media and could be helpful in selecting relevant features. In this paper, we study a novel problem to conduct unsupervised streaming feature selection for social media data. We investigate how to exploit link information in streaming feature selection, resulting in a novel unsupervised streaming feature selection framework USFS. Experimental results on two real-world social media datasets show the effectiveness and efficiency of the proposed framework comparing with the state-of-the-art unsupervised feature selection algorithms.

KW - Social media data

KW - Streaming features

KW - Unsupervised feature selection

UR - http://www.scopus.com/inward/record.url?scp=84958245370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958245370&partnerID=8YFLogxK

U2 - 10.1145/2806416.2806501

DO - 10.1145/2806416.2806501

M3 - Conference contribution

SN - 9781450337946

VL - 19-23-Oct-2015

SP - 1041

EP - 1050

BT - International Conference on Information and Knowledge Management, Proceedings

PB - Association for Computing Machinery

ER -