Empirical analysis of implicit brand networks on social media

Kunpeng Zhang, Siddhartha Bhattacharyya, Sudha Ram

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

2 Citations (Scopus)

Abstract

This paper investigates characteristics of implicit brand networks extracted from a large dataset of user historical activities on a social media platform. To our knowledge, this is one of the first studies to comprehensively examine brands by incorporating user-generated social content and information about user interactions. This paper makes several important contributions. We build and normalize a weighted, undirected network representing interactions among users and brands. We then explore the structure of this network using modified network measures to understand its characteristics and implications. As a part of this exploration, we address three important research questions: (1) What is the structure of a brand-brand network? (2) Does an influential brand have a large number of fans? (3) Does an influential brand receive more positive or more negative comments from social users? Experiments conducted with Facebook data show that the influence of a brand has (a) high positive correlation with the size of a brand, meaning that an influential brand can attract more fans, and, (b) low negative correlation with the sentiment of comments made by users on that brand, which means that negative comments have a more powerful ability to generate awareness of a brand than positive comments. To process the large-scale datasets and networks, we implement MapReduce-based algorithms.

Original languageEnglish (US)
Title of host publicationHT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media
PublisherAssociation for Computing Machinery
Pages190-199
Number of pages10
ISBN (Print)9781450329545
DOIs
StatePublished - 2014
Event25th ACM Conference on Hypertext and Social Media, HT 2014 - Santiago, Chile
Duration: Sep 1 2014Sep 4 2014

Other

Other25th ACM Conference on Hypertext and Social Media, HT 2014
CountryChile
CitySantiago
Period9/1/149/4/14

Fingerprint

Fans
Experiments

Keywords

  • mapreduce
  • marketing intelligence
  • network analysis
  • sentiment identification
  • social media

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Zhang, K., Bhattacharyya, S., & Ram, S. (2014). Empirical analysis of implicit brand networks on social media. In HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media (pp. 190-199). Association for Computing Machinery. https://doi.org/10.1145/2631775.2631806

Empirical analysis of implicit brand networks on social media. / Zhang, Kunpeng; Bhattacharyya, Siddhartha; Ram, Sudha.

HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, 2014. p. 190-199.

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

Zhang, K, Bhattacharyya, S & Ram, S 2014, Empirical analysis of implicit brand networks on social media. in HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, pp. 190-199, 25th ACM Conference on Hypertext and Social Media, HT 2014, Santiago, Chile, 9/1/14. https://doi.org/10.1145/2631775.2631806
Zhang K, Bhattacharyya S, Ram S. Empirical analysis of implicit brand networks on social media. In HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery. 2014. p. 190-199 https://doi.org/10.1145/2631775.2631806
Zhang, Kunpeng ; Bhattacharyya, Siddhartha ; Ram, Sudha. / Empirical analysis of implicit brand networks on social media. HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, 2014. pp. 190-199
@inproceedings{0e673d1dcfc5478b902c4e81d227ecd2,
title = "Empirical analysis of implicit brand networks on social media",
abstract = "This paper investigates characteristics of implicit brand networks extracted from a large dataset of user historical activities on a social media platform. To our knowledge, this is one of the first studies to comprehensively examine brands by incorporating user-generated social content and information about user interactions. This paper makes several important contributions. We build and normalize a weighted, undirected network representing interactions among users and brands. We then explore the structure of this network using modified network measures to understand its characteristics and implications. As a part of this exploration, we address three important research questions: (1) What is the structure of a brand-brand network? (2) Does an influential brand have a large number of fans? (3) Does an influential brand receive more positive or more negative comments from social users? Experiments conducted with Facebook data show that the influence of a brand has (a) high positive correlation with the size of a brand, meaning that an influential brand can attract more fans, and, (b) low negative correlation with the sentiment of comments made by users on that brand, which means that negative comments have a more powerful ability to generate awareness of a brand than positive comments. To process the large-scale datasets and networks, we implement MapReduce-based algorithms.",
keywords = "mapreduce, marketing intelligence, network analysis, sentiment identification, social media",
author = "Kunpeng Zhang and Siddhartha Bhattacharyya and Sudha Ram",
year = "2014",
doi = "10.1145/2631775.2631806",
language = "English (US)",
isbn = "9781450329545",
pages = "190--199",
booktitle = "HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Empirical analysis of implicit brand networks on social media

AU - Zhang, Kunpeng

AU - Bhattacharyya, Siddhartha

AU - Ram, Sudha

PY - 2014

Y1 - 2014

N2 - This paper investigates characteristics of implicit brand networks extracted from a large dataset of user historical activities on a social media platform. To our knowledge, this is one of the first studies to comprehensively examine brands by incorporating user-generated social content and information about user interactions. This paper makes several important contributions. We build and normalize a weighted, undirected network representing interactions among users and brands. We then explore the structure of this network using modified network measures to understand its characteristics and implications. As a part of this exploration, we address three important research questions: (1) What is the structure of a brand-brand network? (2) Does an influential brand have a large number of fans? (3) Does an influential brand receive more positive or more negative comments from social users? Experiments conducted with Facebook data show that the influence of a brand has (a) high positive correlation with the size of a brand, meaning that an influential brand can attract more fans, and, (b) low negative correlation with the sentiment of comments made by users on that brand, which means that negative comments have a more powerful ability to generate awareness of a brand than positive comments. To process the large-scale datasets and networks, we implement MapReduce-based algorithms.

AB - This paper investigates characteristics of implicit brand networks extracted from a large dataset of user historical activities on a social media platform. To our knowledge, this is one of the first studies to comprehensively examine brands by incorporating user-generated social content and information about user interactions. This paper makes several important contributions. We build and normalize a weighted, undirected network representing interactions among users and brands. We then explore the structure of this network using modified network measures to understand its characteristics and implications. As a part of this exploration, we address three important research questions: (1) What is the structure of a brand-brand network? (2) Does an influential brand have a large number of fans? (3) Does an influential brand receive more positive or more negative comments from social users? Experiments conducted with Facebook data show that the influence of a brand has (a) high positive correlation with the size of a brand, meaning that an influential brand can attract more fans, and, (b) low negative correlation with the sentiment of comments made by users on that brand, which means that negative comments have a more powerful ability to generate awareness of a brand than positive comments. To process the large-scale datasets and networks, we implement MapReduce-based algorithms.

KW - mapreduce

KW - marketing intelligence

KW - network analysis

KW - sentiment identification

KW - social media

UR - http://www.scopus.com/inward/record.url?scp=84907403226&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907403226&partnerID=8YFLogxK

U2 - 10.1145/2631775.2631806

DO - 10.1145/2631775.2631806

M3 - Conference contribution

AN - SCOPUS:84907403226

SN - 9781450329545

SP - 190

EP - 199

BT - HT 2014 - Proceedings of the 25th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery

ER -