Tracking sentiment and topic dynamics from social media

Yulan He, Chenghua Lin, Wei Gao, Kam Fai Wong

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

We propose a dynamic joint sentiment-topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic specific word distributions are generated according to the word distributions at previous epochs. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.

Original languageEnglish
Title of host publicationSocial Media Content Analysis
Subtitle of host publicationNatural Language Processing and Beyond
PublisherWorld Scientific Publishing Co. Pte Ltd
Pages457-465
Number of pages9
ISBN (Electronic)9789813223615
ISBN (Print)9789813223608
DOIs
Publication statusPublished - 1 Jan 2017

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

He, Y., Lin, C., Gao, W., & Wong, K. F. (2017). Tracking sentiment and topic dynamics from social media. In Social Media Content Analysis: Natural Language Processing and Beyond (pp. 457-465). World Scientific Publishing Co. Pte Ltd. https://doi.org/10.1142/9789813223615_0028

Tracking sentiment and topic dynamics from social media. / He, Yulan; Lin, Chenghua; Gao, Wei; Wong, Kam Fai.

Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. p. 457-465.

Research output: Chapter in Book/Report/Conference proceedingChapter

He, Y, Lin, C, Gao, W & Wong, KF 2017, Tracking sentiment and topic dynamics from social media. in Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, pp. 457-465. https://doi.org/10.1142/9789813223615_0028
He Y, Lin C, Gao W, Wong KF. Tracking sentiment and topic dynamics from social media. In Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd. 2017. p. 457-465 https://doi.org/10.1142/9789813223615_0028
He, Yulan ; Lin, Chenghua ; Gao, Wei ; Wong, Kam Fai. / Tracking sentiment and topic dynamics from social media. Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. pp. 457-465
@inbook{74d63f6e5f794afba54aea56354c7d20,
title = "Tracking sentiment and topic dynamics from social media",
abstract = "We propose a dynamic joint sentiment-topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic specific word distributions are generated according to the word distributions at previous epochs. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.",
author = "Yulan He and Chenghua Lin and Wei Gao and Wong, {Kam Fai}",
year = "2017",
month = "1",
day = "1",
doi = "10.1142/9789813223615_0028",
language = "English",
isbn = "9789813223608",
pages = "457--465",
booktitle = "Social Media Content Analysis",
publisher = "World Scientific Publishing Co. Pte Ltd",
address = "Singapore",

}

TY - CHAP

T1 - Tracking sentiment and topic dynamics from social media

AU - He, Yulan

AU - Lin, Chenghua

AU - Gao, Wei

AU - Wong, Kam Fai

PY - 2017/1/1

Y1 - 2017/1/1

N2 - We propose a dynamic joint sentiment-topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic specific word distributions are generated according to the word distributions at previous epochs. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.

AB - We propose a dynamic joint sentiment-topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic specific word distributions are generated according to the word distributions at previous epochs. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011.

UR - http://www.scopus.com/inward/record.url?scp=85041613385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041613385&partnerID=8YFLogxK

U2 - 10.1142/9789813223615_0028

DO - 10.1142/9789813223615_0028

M3 - Chapter

AN - SCOPUS:85041613385

SN - 9789813223608

SP - 457

EP - 465

BT - Social Media Content Analysis

PB - World Scientific Publishing Co. Pte Ltd

ER -