Disentangling User Samples: A Supervised Machine Learning Approach to Proxy-population Mismatch in Twitter Research

Kyounghee Kwon, J. Hunter Priniski, Monica Chadha

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This study addresses the issue of sampling biases in social media data-driven communication research. The authors demonstrate how supervised machine learning could reduce Twitter sampling bias induced from “proxy-population mismatch”. Particularly, this study used the Random Forest (RF) classifier to disentangle tweet samples representative of general publics’ activities from non-general—or institutional—activities. By applying RF classifier models to Twitter data sets relevant to four news events and a randomly pooled dataset, the study finds systematic differences between general user samples and institutional user samples in their messaging patterns. This article calls for disentangling Twitter user samples when ordinary user behaviors are the focus of research. It also builds on the development of machine learning modeling in the context of communication research.

Original languageEnglish (US)
Pages (from-to)1-22
Number of pages22
JournalCommunication Methods and Measures
DOIs
StateAccepted/In press - Feb 16 2018

Fingerprint

twitter
mismatch
Learning systems
communication research
Classifiers
Sampling
learning
Communication
trend
social media
news
event

ASJC Scopus subject areas

  • Communication

Cite this

@article{8bf4b9137426407ca705e550cfb2cf18,
title = "Disentangling User Samples: A Supervised Machine Learning Approach to Proxy-population Mismatch in Twitter Research",
abstract = "This study addresses the issue of sampling biases in social media data-driven communication research. The authors demonstrate how supervised machine learning could reduce Twitter sampling bias induced from “proxy-population mismatch”. Particularly, this study used the Random Forest (RF) classifier to disentangle tweet samples representative of general publics’ activities from non-general—or institutional—activities. By applying RF classifier models to Twitter data sets relevant to four news events and a randomly pooled dataset, the study finds systematic differences between general user samples and institutional user samples in their messaging patterns. This article calls for disentangling Twitter user samples when ordinary user behaviors are the focus of research. It also builds on the development of machine learning modeling in the context of communication research.",
author = "Kyounghee Kwon and Priniski, {J. Hunter} and Monica Chadha",
year = "2018",
month = "2",
day = "16",
doi = "10.1080/19312458.2018.1430755",
language = "English (US)",
pages = "1--22",
journal = "Communication Methods and Measures",
issn = "1931-2458",
publisher = "Routledge",

}

TY - JOUR

T1 - Disentangling User Samples

T2 - A Supervised Machine Learning Approach to Proxy-population Mismatch in Twitter Research

AU - Kwon, Kyounghee

AU - Priniski, J. Hunter

AU - Chadha, Monica

PY - 2018/2/16

Y1 - 2018/2/16

N2 - This study addresses the issue of sampling biases in social media data-driven communication research. The authors demonstrate how supervised machine learning could reduce Twitter sampling bias induced from “proxy-population mismatch”. Particularly, this study used the Random Forest (RF) classifier to disentangle tweet samples representative of general publics’ activities from non-general—or institutional—activities. By applying RF classifier models to Twitter data sets relevant to four news events and a randomly pooled dataset, the study finds systematic differences between general user samples and institutional user samples in their messaging patterns. This article calls for disentangling Twitter user samples when ordinary user behaviors are the focus of research. It also builds on the development of machine learning modeling in the context of communication research.

AB - This study addresses the issue of sampling biases in social media data-driven communication research. The authors demonstrate how supervised machine learning could reduce Twitter sampling bias induced from “proxy-population mismatch”. Particularly, this study used the Random Forest (RF) classifier to disentangle tweet samples representative of general publics’ activities from non-general—or institutional—activities. By applying RF classifier models to Twitter data sets relevant to four news events and a randomly pooled dataset, the study finds systematic differences between general user samples and institutional user samples in their messaging patterns. This article calls for disentangling Twitter user samples when ordinary user behaviors are the focus of research. It also builds on the development of machine learning modeling in the context of communication research.

UR - http://www.scopus.com/inward/record.url?scp=85042109394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042109394&partnerID=8YFLogxK

U2 - 10.1080/19312458.2018.1430755

DO - 10.1080/19312458.2018.1430755

M3 - Article

SP - 1

EP - 22

JO - Communication Methods and Measures

JF - Communication Methods and Measures

SN - 1931-2458

ER -