Improved stance prediction in a user similarity feature space

Kareem Darwish, Walid Magdy, Tahar Zanouda

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

3 Citations (Scopus)

Abstract

Predicting the stance of social media users on a topic can be challenging, particularly for users who never express explicit stances. Earlier work has shown that using users’ historical or non-relevant tweets can be used to predict stance. We build on prior work by making use of users’ interaction elements, such as retweeted accounts and mentioned hashtags, to compute the similarities between users and to classify new users in a user similarity feature space. We show that this approach significantly improves stance prediction on two datasets that differ in terms of language, topic, and cultural background.

Original languageEnglish
Title of host publicationProceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017
PublisherAssociation for Computing Machinery, Inc
Pages145-148
Number of pages4
ISBN (Electronic)9781450349932
DOIs
Publication statusPublished - 31 Jul 2017
Event9th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017 - Sydney, Australia
Duration: 31 Jul 20173 Aug 2017

Other

Other9th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017
CountryAustralia
CitySydney
Period31/7/173/8/17

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Darwish, K., Magdy, W., & Zanouda, T. (2017). Improved stance prediction in a user similarity feature space. In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017 (pp. 145-148). Association for Computing Machinery, Inc. https://doi.org/10.1145/3110025.3110112

Improved stance prediction in a user similarity feature space. / Darwish, Kareem; Magdy, Walid; Zanouda, Tahar.

Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc, 2017. p. 145-148.

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

Darwish, K, Magdy, W & Zanouda, T 2017, Improved stance prediction in a user similarity feature space. in Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc, pp. 145-148, 9th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017, Sydney, Australia, 31/7/17. https://doi.org/10.1145/3110025.3110112
Darwish K, Magdy W, Zanouda T. Improved stance prediction in a user similarity feature space. In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc. 2017. p. 145-148 https://doi.org/10.1145/3110025.3110112
Darwish, Kareem ; Magdy, Walid ; Zanouda, Tahar. / Improved stance prediction in a user similarity feature space. Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc, 2017. pp. 145-148
@inproceedings{6e5fdadb999b4216998a3b859b3fe86c,
title = "Improved stance prediction in a user similarity feature space",
abstract = "Predicting the stance of social media users on a topic can be challenging, particularly for users who never express explicit stances. Earlier work has shown that using users’ historical or non-relevant tweets can be used to predict stance. We build on prior work by making use of users’ interaction elements, such as retweeted accounts and mentioned hashtags, to compute the similarities between users and to classify new users in a user similarity feature space. We show that this approach significantly improves stance prediction on two datasets that differ in terms of language, topic, and cultural background.",
author = "Kareem Darwish and Walid Magdy and Tahar Zanouda",
year = "2017",
month = "7",
day = "31",
doi = "10.1145/3110025.3110112",
language = "English",
pages = "145--148",
booktitle = "Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Improved stance prediction in a user similarity feature space

AU - Darwish, Kareem

AU - Magdy, Walid

AU - Zanouda, Tahar

PY - 2017/7/31

Y1 - 2017/7/31

N2 - Predicting the stance of social media users on a topic can be challenging, particularly for users who never express explicit stances. Earlier work has shown that using users’ historical or non-relevant tweets can be used to predict stance. We build on prior work by making use of users’ interaction elements, such as retweeted accounts and mentioned hashtags, to compute the similarities between users and to classify new users in a user similarity feature space. We show that this approach significantly improves stance prediction on two datasets that differ in terms of language, topic, and cultural background.

AB - Predicting the stance of social media users on a topic can be challenging, particularly for users who never express explicit stances. Earlier work has shown that using users’ historical or non-relevant tweets can be used to predict stance. We build on prior work by making use of users’ interaction elements, such as retweeted accounts and mentioned hashtags, to compute the similarities between users and to classify new users in a user similarity feature space. We show that this approach significantly improves stance prediction on two datasets that differ in terms of language, topic, and cultural background.

UR - http://www.scopus.com/inward/record.url?scp=85040252616&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040252616&partnerID=8YFLogxK

U2 - 10.1145/3110025.3110112

DO - 10.1145/3110025.3110112

M3 - Conference contribution

AN - SCOPUS:85040252616

SP - 145

EP - 148

BT - Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017

PB - Association for Computing Machinery, Inc

ER -