Mining phase evolution for hot topics

A case study from multiple social media platforms

Ruoran Liu, Qiudan Li, Can Wang, Lei Wang, Dajun Zeng, Hongyuan Ma

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

1 Citation (Scopus)

Abstract

Monitoring the evolution phases of real-time eventmincluding occurrence, development, climax, decline and ending ismcrucial for management department to intuitively and comprehensively understand the event and then make better decisions. However, there have been very few studies on performing phase evolution analysis of event using the number of posts at the specific time unit. The challenge of this problem is how to identify temporal pattern and mine topic of different phases automatically. In this paper, we propose a unified phase evolution mining model, it firstly identifies the temporal patterns of phases based on k-means and empirical rules, then, burst detection algorithm is adopted to discover peak interval of all phases, finally, we use a summarization technique TextRank to extract keywords from contents to summarize the topics in each phase. In addition, we perform experiments on two real-world datasets collected from different social media platform to understand the event evolution in a more comprehensive way. Experimental results show the characteristics of event evolution on different social media platforms and verify the efficacy of the proposed model.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2814-2819
Number of pages6
Volume2017-January
ISBN (Electronic)9781538616451
DOIs
StatePublished - Nov 27 2017
Event2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 - Banff, Canada
Duration: Oct 5 2017Oct 8 2017

Other

Other2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
CountryCanada
CityBanff
Period10/5/1710/8/17

Fingerprint

Social Media
Mining
Monitoring
Experiments
Summarization
K-means
Burst
Efficacy
Verify
Real-time
Interval
Unit
Experimental Results
Model
Experiment

Keywords

  • Burst detection
  • K-means
  • Phase evolution
  • Social media
  • Textrank

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Control and Optimization

Cite this

Liu, R., Li, Q., Wang, C., Wang, L., Zeng, D., & Ma, H. (2017). Mining phase evolution for hot topics: A case study from multiple social media platforms. In 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017 (Vol. 2017-January, pp. 2814-2819). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2017.8123053

Mining phase evolution for hot topics : A case study from multiple social media platforms. / Liu, Ruoran; Li, Qiudan; Wang, Can; Wang, Lei; Zeng, Dajun; Ma, Hongyuan.

2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 2814-2819.

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

Liu, R, Li, Q, Wang, C, Wang, L, Zeng, D & Ma, H 2017, Mining phase evolution for hot topics: A case study from multiple social media platforms. in 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 2814-2819, 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017, Banff, Canada, 10/5/17. https://doi.org/10.1109/SMC.2017.8123053
Liu R, Li Q, Wang C, Wang L, Zeng D, Ma H. Mining phase evolution for hot topics: A case study from multiple social media platforms. In 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2814-2819 https://doi.org/10.1109/SMC.2017.8123053
Liu, Ruoran ; Li, Qiudan ; Wang, Can ; Wang, Lei ; Zeng, Dajun ; Ma, Hongyuan. / Mining phase evolution for hot topics : A case study from multiple social media platforms. 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2814-2819
@inproceedings{0f62f8aef2d341e0b9f4c059c4e81572,
title = "Mining phase evolution for hot topics: A case study from multiple social media platforms",
abstract = "Monitoring the evolution phases of real-time eventmincluding occurrence, development, climax, decline and ending ismcrucial for management department to intuitively and comprehensively understand the event and then make better decisions. However, there have been very few studies on performing phase evolution analysis of event using the number of posts at the specific time unit. The challenge of this problem is how to identify temporal pattern and mine topic of different phases automatically. In this paper, we propose a unified phase evolution mining model, it firstly identifies the temporal patterns of phases based on k-means and empirical rules, then, burst detection algorithm is adopted to discover peak interval of all phases, finally, we use a summarization technique TextRank to extract keywords from contents to summarize the topics in each phase. In addition, we perform experiments on two real-world datasets collected from different social media platform to understand the event evolution in a more comprehensive way. Experimental results show the characteristics of event evolution on different social media platforms and verify the efficacy of the proposed model.",
keywords = "Burst detection, K-means, Phase evolution, Social media, Textrank",
author = "Ruoran Liu and Qiudan Li and Can Wang and Lei Wang and Dajun Zeng and Hongyuan Ma",
year = "2017",
month = "11",
day = "27",
doi = "10.1109/SMC.2017.8123053",
language = "English (US)",
volume = "2017-January",
pages = "2814--2819",
booktitle = "2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Mining phase evolution for hot topics

T2 - A case study from multiple social media platforms

AU - Liu, Ruoran

AU - Li, Qiudan

AU - Wang, Can

AU - Wang, Lei

AU - Zeng, Dajun

AU - Ma, Hongyuan

PY - 2017/11/27

Y1 - 2017/11/27

N2 - Monitoring the evolution phases of real-time eventmincluding occurrence, development, climax, decline and ending ismcrucial for management department to intuitively and comprehensively understand the event and then make better decisions. However, there have been very few studies on performing phase evolution analysis of event using the number of posts at the specific time unit. The challenge of this problem is how to identify temporal pattern and mine topic of different phases automatically. In this paper, we propose a unified phase evolution mining model, it firstly identifies the temporal patterns of phases based on k-means and empirical rules, then, burst detection algorithm is adopted to discover peak interval of all phases, finally, we use a summarization technique TextRank to extract keywords from contents to summarize the topics in each phase. In addition, we perform experiments on two real-world datasets collected from different social media platform to understand the event evolution in a more comprehensive way. Experimental results show the characteristics of event evolution on different social media platforms and verify the efficacy of the proposed model.

AB - Monitoring the evolution phases of real-time eventmincluding occurrence, development, climax, decline and ending ismcrucial for management department to intuitively and comprehensively understand the event and then make better decisions. However, there have been very few studies on performing phase evolution analysis of event using the number of posts at the specific time unit. The challenge of this problem is how to identify temporal pattern and mine topic of different phases automatically. In this paper, we propose a unified phase evolution mining model, it firstly identifies the temporal patterns of phases based on k-means and empirical rules, then, burst detection algorithm is adopted to discover peak interval of all phases, finally, we use a summarization technique TextRank to extract keywords from contents to summarize the topics in each phase. In addition, we perform experiments on two real-world datasets collected from different social media platform to understand the event evolution in a more comprehensive way. Experimental results show the characteristics of event evolution on different social media platforms and verify the efficacy of the proposed model.

KW - Burst detection

KW - K-means

KW - Phase evolution

KW - Social media

KW - Textrank

UR - http://www.scopus.com/inward/record.url?scp=85044240442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044240442&partnerID=8YFLogxK

U2 - 10.1109/SMC.2017.8123053

DO - 10.1109/SMC.2017.8123053

M3 - Conference contribution

VL - 2017-January

SP - 2814

EP - 2819

BT - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -