Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP

Yuhao Zhang; Wenji Mao; Daniel Zeng

doi:10.1109/ISI.2017.8004885

Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP

Yuhao Zhang, Wenji Mao, Daniel Zeng

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Scopus citations

Abstract

Social media has become an important platform for people to express opinions, share information and communicate with others. Detecting and tracking topics from social media can help people grasp essential information and facilitate many security-related applications. As social media texts are usually short, traditional topic evolution models built based on LDA or HDP often suffer from the data sparsity problem. Recently proposed topic evolution models are more suitable for short texts, but they need to manually specify topic number which is fixed during different time period. To address these issues, in this paper, we propose a nonparametric topic evolution model for social media short texts. We first propose the recurrent semantic dependent Chinese restaurant process (rsdCRP), which is a nonparametric process incorporating word embeddings to capture semantic similarity information. Then we combine rsdCRP with word co-occurrence modeling and build our short-Text oriented topic evolution model sdTEM. We carry out experimental studies on Twitter dataset. The results demonstrate the effectiveness of our method to monitor social media topic evolution compared to the baseline methods.

Original language	English (US)
Title of host publication	2017 IEEE International Conference on Intelligence and Security Informatics
Subtitle of host publication	Security and Big Data, ISI 2017
Editors	Lina Zhou, G. Alan Wang, Chunxiao Xing, Bo Luo, Xiaolong Zheng, Hui Zhang
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	119-124
Number of pages	6
ISBN (Electronic)	9781509067275
DOIs	https://doi.org/10.1109/ISI.2017.8004885
State	Published - Aug 8 2017
Externally published	Yes
Event	15th IEEE International Conference on Intelligence and Security Informatics, ISI 2017 - Beijing, China Duration: Jul 22 2017 → Jul 24 2017

Publication series

Name	2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017

Other

Other	15th IEEE International Conference on Intelligence and Security Informatics, ISI 2017
Country/Territory	China
City	Beijing
Period	7/22/17 → 7/24/17

Keywords

Social Media Analytics
Text Mining
Topic Modeling

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems
Information Systems and Management
Safety, Risk, Reliability and Quality

Access to Document

10.1109/ISI.2017.8004885

Cite this

Zhang, Y., Mao, W., & Zeng, D. (2017). Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP. In L. Zhou, G. A. Wang, C. Xing, B. Luo, X. Zheng, & H. Zhang (Eds.), 2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017 (pp. 119-124). [8004885] (2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISI.2017.8004885

Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP. / Zhang, Yuhao; Mao, Wenji; Zeng, Daniel.

2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017. ed. / Lina Zhou; G. Alan Wang; Chunxiao Xing; Bo Luo; Xiaolong Zheng; Hui Zhang. Institute of Electrical and Electronics Engineers Inc., 2017. p. 119-124 8004885 (2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, Y, Mao, W & Zeng, D 2017, Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP. in L Zhou, GA Wang, C Xing, B Luo, X Zheng & H Zhang (eds), 2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017., 8004885, 2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017, Institute of Electrical and Electronics Engineers Inc., pp. 119-124, 15th IEEE International Conference on Intelligence and Security Informatics, ISI 2017, Beijing, China, 7/22/17. https://doi.org/10.1109/ISI.2017.8004885

Zhang Y, Mao W, Zeng D. Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP. In Zhou L, Wang GA, Xing C, Luo B, Zheng X, Zhang H, editors, 2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 119-124. 8004885. (2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017). https://doi.org/10.1109/ISI.2017.8004885

Zhang, Yuhao ; Mao, Wenji ; Zeng, Daniel. / Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP. 2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017. editor / Lina Zhou ; G. Alan Wang ; Chunxiao Xing ; Bo Luo ; Xiaolong Zheng ; Hui Zhang. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 119-124 (2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017).

@inproceedings{aca756fd4e054e95a04a54bc4dd202a4,

title = "Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP",

abstract = "Social media has become an important platform for people to express opinions, share information and communicate with others. Detecting and tracking topics from social media can help people grasp essential information and facilitate many security-related applications. As social media texts are usually short, traditional topic evolution models built based on LDA or HDP often suffer from the data sparsity problem. Recently proposed topic evolution models are more suitable for short texts, but they need to manually specify topic number which is fixed during different time period. To address these issues, in this paper, we propose a nonparametric topic evolution model for social media short texts. We first propose the recurrent semantic dependent Chinese restaurant process (rsdCRP), which is a nonparametric process incorporating word embeddings to capture semantic similarity information. Then we combine rsdCRP with word co-occurrence modeling and build our short-Text oriented topic evolution model sdTEM. We carry out experimental studies on Twitter dataset. The results demonstrate the effectiveness of our method to monitor social media topic evolution compared to the baseline methods.",

keywords = "Social Media Analytics, Text Mining, Topic Modeling",

author = "Yuhao Zhang and Wenji Mao and Daniel Zeng",

note = "Funding Information: This work is supported in part by NSFC Grant #71621002, the Ministry of Science and Technology of China Major Grant #2016QY02D0205, and CAS Key Grant #ZDRW-XH-2017-3. Publisher Copyright: {\textcopyright} 2017 IEEE.; 15th IEEE International Conference on Intelligence and Security Informatics, ISI 2017 ; Conference date: 22-07-2017 Through 24-07-2017",

year = "2017",

month = aug,

day = "8",

doi = "10.1109/ISI.2017.8004885",

language = "English (US)",

series = "2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "119--124",

editor = "Lina Zhou and Wang, {G. Alan} and Chunxiao Xing and Bo Luo and Xiaolong Zheng and Hui Zhang",

booktitle = "2017 IEEE International Conference on Intelligence and Security Informatics",

}

TY - GEN

T1 - Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP

AU - Zhang, Yuhao

AU - Mao, Wenji

AU - Zeng, Daniel

N1 - Funding Information: This work is supported in part by NSFC Grant #71621002, the Ministry of Science and Technology of China Major Grant #2016QY02D0205, and CAS Key Grant #ZDRW-XH-2017-3. Publisher Copyright: © 2017 IEEE.

PY - 2017/8/8

Y1 - 2017/8/8

N2 - Social media has become an important platform for people to express opinions, share information and communicate with others. Detecting and tracking topics from social media can help people grasp essential information and facilitate many security-related applications. As social media texts are usually short, traditional topic evolution models built based on LDA or HDP often suffer from the data sparsity problem. Recently proposed topic evolution models are more suitable for short texts, but they need to manually specify topic number which is fixed during different time period. To address these issues, in this paper, we propose a nonparametric topic evolution model for social media short texts. We first propose the recurrent semantic dependent Chinese restaurant process (rsdCRP), which is a nonparametric process incorporating word embeddings to capture semantic similarity information. Then we combine rsdCRP with word co-occurrence modeling and build our short-Text oriented topic evolution model sdTEM. We carry out experimental studies on Twitter dataset. The results demonstrate the effectiveness of our method to monitor social media topic evolution compared to the baseline methods.

AB - Social media has become an important platform for people to express opinions, share information and communicate with others. Detecting and tracking topics from social media can help people grasp essential information and facilitate many security-related applications. As social media texts are usually short, traditional topic evolution models built based on LDA or HDP often suffer from the data sparsity problem. Recently proposed topic evolution models are more suitable for short texts, but they need to manually specify topic number which is fixed during different time period. To address these issues, in this paper, we propose a nonparametric topic evolution model for social media short texts. We first propose the recurrent semantic dependent Chinese restaurant process (rsdCRP), which is a nonparametric process incorporating word embeddings to capture semantic similarity information. Then we combine rsdCRP with word co-occurrence modeling and build our short-Text oriented topic evolution model sdTEM. We carry out experimental studies on Twitter dataset. The results demonstrate the effectiveness of our method to monitor social media topic evolution compared to the baseline methods.

KW - Social Media Analytics

KW - Text Mining

KW - Topic Modeling

UR - http://www.scopus.com/inward/record.url?scp=85030233335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030233335&partnerID=8YFLogxK

U2 - 10.1109/ISI.2017.8004885

DO - 10.1109/ISI.2017.8004885

M3 - Conference contribution

AN - SCOPUS:85030233335

T3 - 2017 IEEE International Conference on Intelligence and Security Informatics: Security and Big Data, ISI 2017

SP - 119

EP - 124

BT - 2017 IEEE International Conference on Intelligence and Security Informatics

A2 - Zhou, Lina

A2 - Wang, G. Alan

A2 - Xing, Chunxiao

A2 - Luo, Bo

A2 - Zheng, Xiaolong

A2 - Zhang, Hui

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE International Conference on Intelligence and Security Informatics, ISI 2017

Y2 - 22 July 2017 through 24 July 2017

ER -

Topic evolution modeling in social media short texts based on recurrent semantic dependent CRP

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this