Listening to the crowd: Automated analysis of events via aggregated twitter sentiment

Yuheng Hu, Fei Wang, Subbarao Kambhampati

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

26 Citations (Scopus)

Abstract

Individuals often express their opinions on social media platforms like Twitter and Facebook during public events such as the U.S. Presidential debate and the Oscar awards ceremony. Gleaning insights from these posts is of importance to analyzing the impact of the event. In this work, we consider the problem of identifying the segments and topics of an event that garnered praise or criticism, according to aggregated Twitter responses. We propose a flexible factorization framework, SOCSENT, to learn factors about segments, topics, and sentiments. To regulate the learning process, several constraints based on prior knowledge on sentiment lexicon, sentiment orientations (on a few tweets) as well as tweets alignments to the event are enforced. We implement our approach using simple update rules to get the optimal solution. We evaluate the proposed method both quantitatively and qualitatively on two large-scale tweet datasets associated with two events from different domains to show that it improves significantly over baseline models.

Original languageEnglish (US)
Title of host publicationIJCAI International Joint Conference on Artificial Intelligence
Pages2640-2646
Number of pages7
StatePublished - 2013
Event23rd International Joint Conference on Artificial Intelligence, IJCAI 2013 - Beijing, China
Duration: Aug 3 2013Aug 9 2013

Other

Other23rd International Joint Conference on Artificial Intelligence, IJCAI 2013
CountryChina
CityBeijing
Period8/3/138/9/13

Fingerprint

Factorization

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Hu, Y., Wang, F., & Kambhampati, S. (2013). Listening to the crowd: Automated analysis of events via aggregated twitter sentiment. In IJCAI International Joint Conference on Artificial Intelligence (pp. 2640-2646)

Listening to the crowd : Automated analysis of events via aggregated twitter sentiment. / Hu, Yuheng; Wang, Fei; Kambhampati, Subbarao.

IJCAI International Joint Conference on Artificial Intelligence. 2013. p. 2640-2646.

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

Hu, Y, Wang, F & Kambhampati, S 2013, Listening to the crowd: Automated analysis of events via aggregated twitter sentiment. in IJCAI International Joint Conference on Artificial Intelligence. pp. 2640-2646, 23rd International Joint Conference on Artificial Intelligence, IJCAI 2013, Beijing, China, 8/3/13.
Hu Y, Wang F, Kambhampati S. Listening to the crowd: Automated analysis of events via aggregated twitter sentiment. In IJCAI International Joint Conference on Artificial Intelligence. 2013. p. 2640-2646
Hu, Yuheng ; Wang, Fei ; Kambhampati, Subbarao. / Listening to the crowd : Automated analysis of events via aggregated twitter sentiment. IJCAI International Joint Conference on Artificial Intelligence. 2013. pp. 2640-2646
@inproceedings{a5fa0ea1bc9b44e88900a9fdeb1df5dd,
title = "Listening to the crowd: Automated analysis of events via aggregated twitter sentiment",
abstract = "Individuals often express their opinions on social media platforms like Twitter and Facebook during public events such as the U.S. Presidential debate and the Oscar awards ceremony. Gleaning insights from these posts is of importance to analyzing the impact of the event. In this work, we consider the problem of identifying the segments and topics of an event that garnered praise or criticism, according to aggregated Twitter responses. We propose a flexible factorization framework, SOCSENT, to learn factors about segments, topics, and sentiments. To regulate the learning process, several constraints based on prior knowledge on sentiment lexicon, sentiment orientations (on a few tweets) as well as tweets alignments to the event are enforced. We implement our approach using simple update rules to get the optimal solution. We evaluate the proposed method both quantitatively and qualitatively on two large-scale tweet datasets associated with two events from different domains to show that it improves significantly over baseline models.",
author = "Yuheng Hu and Fei Wang and Subbarao Kambhampati",
year = "2013",
language = "English (US)",
isbn = "9781577356332",
pages = "2640--2646",
booktitle = "IJCAI International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - Listening to the crowd

T2 - Automated analysis of events via aggregated twitter sentiment

AU - Hu, Yuheng

AU - Wang, Fei

AU - Kambhampati, Subbarao

PY - 2013

Y1 - 2013

N2 - Individuals often express their opinions on social media platforms like Twitter and Facebook during public events such as the U.S. Presidential debate and the Oscar awards ceremony. Gleaning insights from these posts is of importance to analyzing the impact of the event. In this work, we consider the problem of identifying the segments and topics of an event that garnered praise or criticism, according to aggregated Twitter responses. We propose a flexible factorization framework, SOCSENT, to learn factors about segments, topics, and sentiments. To regulate the learning process, several constraints based on prior knowledge on sentiment lexicon, sentiment orientations (on a few tweets) as well as tweets alignments to the event are enforced. We implement our approach using simple update rules to get the optimal solution. We evaluate the proposed method both quantitatively and qualitatively on two large-scale tweet datasets associated with two events from different domains to show that it improves significantly over baseline models.

AB - Individuals often express their opinions on social media platforms like Twitter and Facebook during public events such as the U.S. Presidential debate and the Oscar awards ceremony. Gleaning insights from these posts is of importance to analyzing the impact of the event. In this work, we consider the problem of identifying the segments and topics of an event that garnered praise or criticism, according to aggregated Twitter responses. We propose a flexible factorization framework, SOCSENT, to learn factors about segments, topics, and sentiments. To regulate the learning process, several constraints based on prior knowledge on sentiment lexicon, sentiment orientations (on a few tweets) as well as tweets alignments to the event are enforced. We implement our approach using simple update rules to get the optimal solution. We evaluate the proposed method both quantitatively and qualitatively on two large-scale tweet datasets associated with two events from different domains to show that it improves significantly over baseline models.

UR - http://www.scopus.com/inward/record.url?scp=84896062601&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896062601&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84896062601

SN - 9781577356332

SP - 2640

EP - 2646

BT - IJCAI International Joint Conference on Artificial Intelligence

ER -