Topic-based content and sentiment analysis of Ebola virus on Twitter and in the news

Erin Hea Jin Kim, Yoo Kyung Jeong, Yuyoung Kim, Keun Young Kang, Min Song

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

The present study investigates topic coverage and sentiment dynamics of two different media sources, Twitter and news publications, on the hot health issue of Ebola. We conduct content and sentiment analysis by: (1) applying vocabulary control to collected datasets; (2) employing the n-gram LDA topic modeling technique; (3) adopting entity extraction and entity network; and (4) introducing the concept of topic-based sentiment scores. With the query term 'Ebola' or 'Ebola virus', we collected 16,189 news articles from 1006 different publications and 7,106,297 tweets with the Twitter stream API. The experiments indicate that topic coverage of Twitter is narrower and more blurry than that of the news media. In terms of sentiment dynamics, the life span and variance of sentiment on Twitter is shorter and smaller than in the news. In addition, we observe that news articles focus more on event-related entities such as person, organization and location, whereas Twitter covers more time-oriented entities. Based on the results, we report on the characteristics of Twitter and news media as two distinct news outlets in terms of content coverage and sentiment dynamics.

Original languageEnglish
Pages (from-to)763-781
Number of pages19
JournalJournal of Information Science
Volume42
Issue number6
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

twitter
Viruses
news
Vocabulary control
Application programming interfaces (API)
coverage
Health
life-span
Experiments
vocabulary
organization
human being
event
experiment
health

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Library and Information Sciences

Cite this

Kim, Erin Hea Jin ; Jeong, Yoo Kyung ; Kim, Yuyoung ; Kang, Keun Young ; Song, Min. / Topic-based content and sentiment analysis of Ebola virus on Twitter and in the news. In: Journal of Information Science. 2015 ; Vol. 42, No. 6. pp. 763-781.
@article{1237e23aa00d40f287dab5e8537dd65f,
title = "Topic-based content and sentiment analysis of Ebola virus on Twitter and in the news",
abstract = "The present study investigates topic coverage and sentiment dynamics of two different media sources, Twitter and news publications, on the hot health issue of Ebola. We conduct content and sentiment analysis by: (1) applying vocabulary control to collected datasets; (2) employing the n-gram LDA topic modeling technique; (3) adopting entity extraction and entity network; and (4) introducing the concept of topic-based sentiment scores. With the query term 'Ebola' or 'Ebola virus', we collected 16,189 news articles from 1006 different publications and 7,106,297 tweets with the Twitter stream API. The experiments indicate that topic coverage of Twitter is narrower and more blurry than that of the news media. In terms of sentiment dynamics, the life span and variance of sentiment on Twitter is shorter and smaller than in the news. In addition, we observe that news articles focus more on event-related entities such as person, organization and location, whereas Twitter covers more time-oriented entities. Based on the results, we report on the characteristics of Twitter and news media as two distinct news outlets in terms of content coverage and sentiment dynamics.",
author = "Kim, {Erin Hea Jin} and Jeong, {Yoo Kyung} and Yuyoung Kim and Kang, {Keun Young} and Min Song",
year = "2015",
month = "1",
day = "1",
doi = "10.1177/0165551515608733",
language = "English",
volume = "42",
pages = "763--781",
journal = "Journal of Information Science",
issn = "0165-5515",
publisher = "SAGE Publications Ltd",
number = "6",

}

Topic-based content and sentiment analysis of Ebola virus on Twitter and in the news. / Kim, Erin Hea Jin; Jeong, Yoo Kyung; Kim, Yuyoung; Kang, Keun Young; Song, Min.

In: Journal of Information Science, Vol. 42, No. 6, 01.01.2015, p. 763-781.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Topic-based content and sentiment analysis of Ebola virus on Twitter and in the news

AU - Kim, Erin Hea Jin

AU - Jeong, Yoo Kyung

AU - Kim, Yuyoung

AU - Kang, Keun Young

AU - Song, Min

PY - 2015/1/1

Y1 - 2015/1/1

N2 - The present study investigates topic coverage and sentiment dynamics of two different media sources, Twitter and news publications, on the hot health issue of Ebola. We conduct content and sentiment analysis by: (1) applying vocabulary control to collected datasets; (2) employing the n-gram LDA topic modeling technique; (3) adopting entity extraction and entity network; and (4) introducing the concept of topic-based sentiment scores. With the query term 'Ebola' or 'Ebola virus', we collected 16,189 news articles from 1006 different publications and 7,106,297 tweets with the Twitter stream API. The experiments indicate that topic coverage of Twitter is narrower and more blurry than that of the news media. In terms of sentiment dynamics, the life span and variance of sentiment on Twitter is shorter and smaller than in the news. In addition, we observe that news articles focus more on event-related entities such as person, organization and location, whereas Twitter covers more time-oriented entities. Based on the results, we report on the characteristics of Twitter and news media as two distinct news outlets in terms of content coverage and sentiment dynamics.

AB - The present study investigates topic coverage and sentiment dynamics of two different media sources, Twitter and news publications, on the hot health issue of Ebola. We conduct content and sentiment analysis by: (1) applying vocabulary control to collected datasets; (2) employing the n-gram LDA topic modeling technique; (3) adopting entity extraction and entity network; and (4) introducing the concept of topic-based sentiment scores. With the query term 'Ebola' or 'Ebola virus', we collected 16,189 news articles from 1006 different publications and 7,106,297 tweets with the Twitter stream API. The experiments indicate that topic coverage of Twitter is narrower and more blurry than that of the news media. In terms of sentiment dynamics, the life span and variance of sentiment on Twitter is shorter and smaller than in the news. In addition, we observe that news articles focus more on event-related entities such as person, organization and location, whereas Twitter covers more time-oriented entities. Based on the results, we report on the characteristics of Twitter and news media as two distinct news outlets in terms of content coverage and sentiment dynamics.

UR - http://www.scopus.com/inward/record.url?scp=85002368675&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002368675&partnerID=8YFLogxK

U2 - 10.1177/0165551515608733

DO - 10.1177/0165551515608733

M3 - Article

AN - SCOPUS:85002368675

VL - 42

SP - 763

EP - 781

JO - Journal of Information Science

JF - Journal of Information Science

SN - 0165-5515

IS - 6

ER -