Cover Image

It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis

Gossips can be dangerous for business, but some of the content helps businesses identify customers' perceptions, thus permitting opportunities to grow. To date, there has been an increase participation in online gossip, in which people utilise platforms like Facebook, blogs and online forums to...

Full description

Saved in:
Bibliographic Details
Main Authors: Drus, Zulfadzli, Khalid, Haliyana
Format: Conference or Workshop Item
Published: 2022
Subjects:
HB Economic Theory
HF Commerce
Online Access:http://eprints.utm.my/id/eprint/99002/
http://dx.doi.org/10.1109/BCD54882.2022.9900719
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.99002
record_format eprints
spelling my.utm.990022023-02-22T03:53:44Z http://eprints.utm.my/id/eprint/99002/ It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis Drus, Zulfadzli Khalid, Haliyana HB Economic Theory HF Commerce Gossips can be dangerous for business, but some of the content helps businesses identify customers' perceptions, thus permitting opportunities to grow. To date, there has been an increase participation in online gossip, in which people utilise platforms like Facebook, blogs and online forums to snoop on and discuss their favourite celebrities. In this study, we propose three approaches for exploring the context and comprehending the content and sentiment users discussed in online gossip threads: Netnography, topic modelling, and sentiment analysis. We retrieved 6055 conversation threads, including three social media celebrity threads, from an online forum called Cari Forum. Using netnography, we were able to identify seven topics in the thread. The thread was then further analysed using the Latent Dirichlet Allocation (LDA) topic modelling approach. We discovered that seven is the optimal number of topics detected in the thread with no overlap. We used the Logistic Regression Model to evaluate each conversation thread's sentiment. We identify each topic's positive and negative sentiment, obtained through our sentiment analysis approach. The three methods helped us to understand consumers' opinions and stories about the lives and businesses of social media celebrities. The implications, research limitations, recommendations for future research and conclusion have been elaborated on in this paper. 2022-08 Conference or Workshop Item PeerReviewed Drus, Zulfadzli and Khalid, Haliyana (2022) It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis. In: 7th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science, BCD 2022, 4 August 2022 - 6 August 2022, Danang, Vietnam. http://dx.doi.org/10.1109/BCD54882.2022.9900719
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic HB Economic Theory
HF Commerce
spellingShingle HB Economic Theory
HF Commerce
Drus, Zulfadzli
Khalid, Haliyana
It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis
description Gossips can be dangerous for business, but some of the content helps businesses identify customers' perceptions, thus permitting opportunities to grow. To date, there has been an increase participation in online gossip, in which people utilise platforms like Facebook, blogs and online forums to snoop on and discuss their favourite celebrities. In this study, we propose three approaches for exploring the context and comprehending the content and sentiment users discussed in online gossip threads: Netnography, topic modelling, and sentiment analysis. We retrieved 6055 conversation threads, including three social media celebrity threads, from an online forum called Cari Forum. Using netnography, we were able to identify seven topics in the thread. The thread was then further analysed using the Latent Dirichlet Allocation (LDA) topic modelling approach. We discovered that seven is the optimal number of topics detected in the thread with no overlap. We used the Logistic Regression Model to evaluate each conversation thread's sentiment. We identify each topic's positive and negative sentiment, obtained through our sentiment analysis approach. The three methods helped us to understand consumers' opinions and stories about the lives and businesses of social media celebrities. The implications, research limitations, recommendations for future research and conclusion have been elaborated on in this paper.
format Conference or Workshop Item
author Drus, Zulfadzli
Khalid, Haliyana
author_facet Drus, Zulfadzli
Khalid, Haliyana
author_sort Drus, Zulfadzli
title It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis
title_short It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis
title_full It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis
title_fullStr It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis
title_full_unstemmed It takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis
title_sort it takes three to tango: understanding the world of online gossips through netnography, big data topic modelling and sentiment analysis
publishDate 2022
url http://eprints.utm.my/id/eprint/99002/
http://dx.doi.org/10.1109/BCD54882.2022.9900719
_version_ 1758578049443430400
score 13.211869

Similar Items