User group based emotion detection and topic discovery over short text

Jiachun FENG; Yanghui RAO; Haoran XIE; Fu Lee WANG; Qing LI

doi:10.1007/s11280-019-00760-3

User group based emotion detection and topic discovery over short text

Jiachun FENG^*, Yanghui RAO, Haoran XIE, Fu Lee WANG, Qing LI

^*Corresponding author for this work

Department of Computing and Decision Sciences

Research output: Journal Publications › Journal Article (refereed) › peer-review

15 Citations (Scopus)

Abstract

In recent years, with the development of social media platforms, more and more people express their emotions online through short messages. It is quite valuable to detect emotions and relevant topics from such data. However, the feature sparsity of short texts brings challenges to joint topic-emotion models. In many cases, it is necessary to know not only what people think of specific topics, but also which individuals have similar feedback, and what characteristics of these users have. In this paper, we propose a user group based topic-emotion model named UGTE for emotions detection and topic discovery, which can alleviate the above feature sparsity problem of short texts. Specifically, the characteristics of each user are used to discover groups of individuals who share similar emotions, and UGTE aggregates short texts within a group into long pseudo-documents effectively. Experiments conducted on a real-world short text dataset validate the effectiveness of our proposed model.

Original language	English
Pages (from-to)	1553-1587
Number of pages	35
Journal	World Wide Web
Volume	23
Issue number	3
Early online date	12 Dec 2019
DOIs	https://doi.org/10.1007/s11280-019-00760-3
Publication status	Published - May 2020

Bibliographical note

This work has been supported by Top-Up Fund (TFG-04) and Seed Fund (SFG-10) for General Research Fund / Early Career Scheme and Interdisciplinary Research Scheme of the Dean’s Research Fund 2018-19 (FLASS/DRF/IDS-3), Departmental Collaborative Research Fund 2019 (MIT/DCRF-R2/18-19), Funding Support to General Research Fund Proposal (RG 39/2019-2020R) and the Internal Research Grant (RG 90/2018-2019R) of The Education University of Hong Kong, and LEO Dr David P. Chan Institute of Data Science, Lingnan University, Hong Kong. The work has also been supported by the Research Grants Council of the Hong Kong Special Administrative Region, China (Collaborative Research Fund, project number C1031-18G).

Keywords

Joint topic-emotion model
Short text modeling
User characteristics
User group based mining

Access to Document

10.1007/s11280-019-00760-3

Cite this

@article{0fe19c0d15e44945998f420790e53b43,

title = "User group based emotion detection and topic discovery over short text",

abstract = "In recent years, with the development of social media platforms, more and more people express their emotions online through short messages. It is quite valuable to detect emotions and relevant topics from such data. However, the feature sparsity of short texts brings challenges to joint topic-emotion models. In many cases, it is necessary to know not only what people think of specific topics, but also which individuals have similar feedback, and what characteristics of these users have. In this paper, we propose a user group based topic-emotion model named UGTE for emotions detection and topic discovery, which can alleviate the above feature sparsity problem of short texts. Specifically, the characteristics of each user are used to discover groups of individuals who share similar emotions, and UGTE aggregates short texts within a group into long pseudo-documents effectively. Experiments conducted on a real-world short text dataset validate the effectiveness of our proposed model.",

keywords = "Joint topic-emotion model, Short text modeling, User characteristics, User group based mining",

author = "Jiachun FENG and Yanghui RAO and Haoran XIE and WANG, {Fu Lee} and Qing LI",

note = "This work has been supported by Top-Up Fund (TFG-04) and Seed Fund (SFG-10) for General Research Fund / Early Career Scheme and Interdisciplinary Research Scheme of the Dean{\textquoteright}s Research Fund 2018-19 (FLASS/DRF/IDS-3), Departmental Collaborative Research Fund 2019 (MIT/DCRF-R2/18-19), Funding Support to General Research Fund Proposal (RG 39/2019-2020R) and the Internal Research Grant (RG 90/2018-2019R) of The Education University of Hong Kong, and LEO Dr David P. Chan Institute of Data Science, Lingnan University, Hong Kong. The work has also been supported by the Research Grants Council of the Hong Kong Special Administrative Region, China (Collaborative Research Fund, project number C1031-18G).",

year = "2020",

month = may,

doi = "10.1007/s11280-019-00760-3",

language = "English",

volume = "23",

pages = "1553--1587",

journal = "World Wide Web",

issn = "1386-145X",

publisher = "Springer New York",

number = "3",

}

TY - JOUR

T1 - User group based emotion detection and topic discovery over short text

AU - FENG, Jiachun

AU - RAO, Yanghui

AU - XIE, Haoran

AU - WANG, Fu Lee

AU - LI, Qing

N1 - This work has been supported by Top-Up Fund (TFG-04) and Seed Fund (SFG-10) for General Research Fund / Early Career Scheme and Interdisciplinary Research Scheme of the Dean’s Research Fund 2018-19 (FLASS/DRF/IDS-3), Departmental Collaborative Research Fund 2019 (MIT/DCRF-R2/18-19), Funding Support to General Research Fund Proposal (RG 39/2019-2020R) and the Internal Research Grant (RG 90/2018-2019R) of The Education University of Hong Kong, and LEO Dr David P. Chan Institute of Data Science, Lingnan University, Hong Kong. The work has also been supported by the Research Grants Council of the Hong Kong Special Administrative Region, China (Collaborative Research Fund, project number C1031-18G).

PY - 2020/5

Y1 - 2020/5

N2 - In recent years, with the development of social media platforms, more and more people express their emotions online through short messages. It is quite valuable to detect emotions and relevant topics from such data. However, the feature sparsity of short texts brings challenges to joint topic-emotion models. In many cases, it is necessary to know not only what people think of specific topics, but also which individuals have similar feedback, and what characteristics of these users have. In this paper, we propose a user group based topic-emotion model named UGTE for emotions detection and topic discovery, which can alleviate the above feature sparsity problem of short texts. Specifically, the characteristics of each user are used to discover groups of individuals who share similar emotions, and UGTE aggregates short texts within a group into long pseudo-documents effectively. Experiments conducted on a real-world short text dataset validate the effectiveness of our proposed model.

AB - In recent years, with the development of social media platforms, more and more people express their emotions online through short messages. It is quite valuable to detect emotions and relevant topics from such data. However, the feature sparsity of short texts brings challenges to joint topic-emotion models. In many cases, it is necessary to know not only what people think of specific topics, but also which individuals have similar feedback, and what characteristics of these users have. In this paper, we propose a user group based topic-emotion model named UGTE for emotions detection and topic discovery, which can alleviate the above feature sparsity problem of short texts. Specifically, the characteristics of each user are used to discover groups of individuals who share similar emotions, and UGTE aggregates short texts within a group into long pseudo-documents effectively. Experiments conducted on a real-world short text dataset validate the effectiveness of our proposed model.

KW - Joint topic-emotion model

KW - Short text modeling

KW - User characteristics

KW - User group based mining

UR - http://www.scopus.com/inward/record.url?scp=85076609107&partnerID=8YFLogxK

U2 - 10.1007/s11280-019-00760-3

DO - 10.1007/s11280-019-00760-3

M3 - Journal Article (refereed)

SN - 1386-145X

VL - 23

SP - 1553

EP - 1587

JO - World Wide Web

JF - World Wide Web

IS - 3

ER -

User group based emotion detection and topic discovery over short text

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this