Dissecting emotion and user influence in social media communities: An interaction modeling approach

Wingyan Chung, Dajun Zeng

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Human emotion expressed in social media plays an increasingly important role in shaping policies and decisions. However, the process by which emotion produces influence in online social media networks is relatively unknown. Previous works focus largely on sentiment classification and polarity identification but do not adequately consider the way emotion affects user influence. This research developed a novel framework, a theory-based model, and a proof-of-concept system for dissecting emotion and user influence in social media networks. The system models emotion-triggered influence and facilitates analysis of emotion-influence causality in the context of U.S. border security (using 5,327,813 tweets posted by 1,303,477 users). Motivated by a theory of emotion spread, the model was integrated in an influence-computation method, called the interaction modeling (IM) approach, which was compared with a benchmark using a user centrality (UC) approach based on social positions. IM was found to have identified influential users who are more broadly related to U.S. cultural issues. Influential users tended to express intense emotions of fear, anger, disgust, and sadness. The emotion trust distinguishes influential users from others, whereas anger and fear contributed significantly to causing user influence. The research contributes to incorporating human emotion into the data-information-knowledge-wisdom model of knowledge management and to providing new information systems artifacts and new causality findings for emotion-influence analysis.

Original languageEnglish (US)
JournalInformation and Management
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Knowledge management
Information systems
Emotion
Modeling
Social media
Interaction
Causality
Anger
Centrality
Disgust
Cultural issues
Benchmark
Integrated
Wisdom
System model
Sentiment classification

Keywords

  • Border security
  • Causal modeling
  • Emotion
  • Emotion extraction
  • Influence modeling
  • Network analysis
  • Sentiment analysis
  • Social computing
  • Social media analytics

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Information Systems and Management

Cite this

@article{bfa80938fc5d4ac69e1b51fa5014780c,
title = "Dissecting emotion and user influence in social media communities: An interaction modeling approach",
abstract = "Human emotion expressed in social media plays an increasingly important role in shaping policies and decisions. However, the process by which emotion produces influence in online social media networks is relatively unknown. Previous works focus largely on sentiment classification and polarity identification but do not adequately consider the way emotion affects user influence. This research developed a novel framework, a theory-based model, and a proof-of-concept system for dissecting emotion and user influence in social media networks. The system models emotion-triggered influence and facilitates analysis of emotion-influence causality in the context of U.S. border security (using 5,327,813 tweets posted by 1,303,477 users). Motivated by a theory of emotion spread, the model was integrated in an influence-computation method, called the interaction modeling (IM) approach, which was compared with a benchmark using a user centrality (UC) approach based on social positions. IM was found to have identified influential users who are more broadly related to U.S. cultural issues. Influential users tended to express intense emotions of fear, anger, disgust, and sadness. The emotion trust distinguishes influential users from others, whereas anger and fear contributed significantly to causing user influence. The research contributes to incorporating human emotion into the data-information-knowledge-wisdom model of knowledge management and to providing new information systems artifacts and new causality findings for emotion-influence analysis.",
keywords = "Border security, Causal modeling, Emotion, Emotion extraction, Influence modeling, Network analysis, Sentiment analysis, Social computing, Social media analytics",
author = "Wingyan Chung and Dajun Zeng",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.im.2018.09.008",
language = "English (US)",
journal = "Information and Management",
issn = "0378-7206",
publisher = "Elsevier",

}

TY - JOUR

T1 - Dissecting emotion and user influence in social media communities

T2 - An interaction modeling approach

AU - Chung, Wingyan

AU - Zeng, Dajun

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Human emotion expressed in social media plays an increasingly important role in shaping policies and decisions. However, the process by which emotion produces influence in online social media networks is relatively unknown. Previous works focus largely on sentiment classification and polarity identification but do not adequately consider the way emotion affects user influence. This research developed a novel framework, a theory-based model, and a proof-of-concept system for dissecting emotion and user influence in social media networks. The system models emotion-triggered influence and facilitates analysis of emotion-influence causality in the context of U.S. border security (using 5,327,813 tweets posted by 1,303,477 users). Motivated by a theory of emotion spread, the model was integrated in an influence-computation method, called the interaction modeling (IM) approach, which was compared with a benchmark using a user centrality (UC) approach based on social positions. IM was found to have identified influential users who are more broadly related to U.S. cultural issues. Influential users tended to express intense emotions of fear, anger, disgust, and sadness. The emotion trust distinguishes influential users from others, whereas anger and fear contributed significantly to causing user influence. The research contributes to incorporating human emotion into the data-information-knowledge-wisdom model of knowledge management and to providing new information systems artifacts and new causality findings for emotion-influence analysis.

AB - Human emotion expressed in social media plays an increasingly important role in shaping policies and decisions. However, the process by which emotion produces influence in online social media networks is relatively unknown. Previous works focus largely on sentiment classification and polarity identification but do not adequately consider the way emotion affects user influence. This research developed a novel framework, a theory-based model, and a proof-of-concept system for dissecting emotion and user influence in social media networks. The system models emotion-triggered influence and facilitates analysis of emotion-influence causality in the context of U.S. border security (using 5,327,813 tweets posted by 1,303,477 users). Motivated by a theory of emotion spread, the model was integrated in an influence-computation method, called the interaction modeling (IM) approach, which was compared with a benchmark using a user centrality (UC) approach based on social positions. IM was found to have identified influential users who are more broadly related to U.S. cultural issues. Influential users tended to express intense emotions of fear, anger, disgust, and sadness. The emotion trust distinguishes influential users from others, whereas anger and fear contributed significantly to causing user influence. The research contributes to incorporating human emotion into the data-information-knowledge-wisdom model of knowledge management and to providing new information systems artifacts and new causality findings for emotion-influence analysis.

KW - Border security

KW - Causal modeling

KW - Emotion

KW - Emotion extraction

KW - Influence modeling

KW - Network analysis

KW - Sentiment analysis

KW - Social computing

KW - Social media analytics

UR - http://www.scopus.com/inward/record.url?scp=85054456877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054456877&partnerID=8YFLogxK

U2 - 10.1016/j.im.2018.09.008

DO - 10.1016/j.im.2018.09.008

M3 - Article

AN - SCOPUS:85054456877

JO - Information and Management

JF - Information and Management

SN - 0378-7206

ER -