News story clustering from both what and how aspects: Using bag of word model and affinity propagation

Wei Ta Chu, Chao Chin Huang, Wen Fang Cheng

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

2 Citations (Scopus)

Abstract

The 24-hour news TV channels repeat the same news stories again and again. In this paper we cluster hundreds of news stories broadcasted in a day into dozens of clusters according to topics, and thus facilitate efficient browsing and summarization. The proposed system automatically removes commercial breaks and detects anchorpersons, and then determines boundaries of news stories. Semantic concepts, the bag of visual word model and the bag of trajectory model are used to describe what and how objects present in news stories. After measuring similarity between stories by the earth mover's distance, the affinity propagation algorithm is utilized to cluster stories of the same topic together. The experimental results show that with the proposed methods sophisticated news stories can be effectively clustered.

Original languageEnglish
Title of host publicationMM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11
Pages7-12
Number of pages6
DOIs
Publication statusPublished - 2011 Dec 1
Event2011 ACM Multimedia Conference, MM'11 and Co-Located Workshops - 2011 ACM International Workshop on Automated Media Analysis and Production for Novel TV Services, AIEMPro'11 - Scottsdale, AZ, United States
Duration: 2011 Nov 282011 Dec 1

Publication series

NameMM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11

Conference

Conference2011 ACM Multimedia Conference, MM'11 and Co-Located Workshops - 2011 ACM International Workshop on Automated Media Analysis and Production for Novel TV Services, AIEMPro'11
CountryUnited States
CityScottsdale, AZ
Period11-11-2811-12-01

Fingerprint

Earth (planet)
Semantics
Trajectories

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Cite this

Chu, W. T., Huang, C. C., & Cheng, W. F. (2011). News story clustering from both what and how aspects: Using bag of word model and affinity propagation. In MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11 (pp. 7-12). (MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11). https://doi.org/10.1145/2072552.2072555
Chu, Wei Ta ; Huang, Chao Chin ; Cheng, Wen Fang. / News story clustering from both what and how aspects : Using bag of word model and affinity propagation. MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11. 2011. pp. 7-12 (MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11).
@inproceedings{de3ed9883f2b4a06bf37bb64dea2243c,
title = "News story clustering from both what and how aspects: Using bag of word model and affinity propagation",
abstract = "The 24-hour news TV channels repeat the same news stories again and again. In this paper we cluster hundreds of news stories broadcasted in a day into dozens of clusters according to topics, and thus facilitate efficient browsing and summarization. The proposed system automatically removes commercial breaks and detects anchorpersons, and then determines boundaries of news stories. Semantic concepts, the bag of visual word model and the bag of trajectory model are used to describe what and how objects present in news stories. After measuring similarity between stories by the earth mover's distance, the affinity propagation algorithm is utilized to cluster stories of the same topic together. The experimental results show that with the proposed methods sophisticated news stories can be effectively clustered.",
author = "Chu, {Wei Ta} and Huang, {Chao Chin} and Cheng, {Wen Fang}",
year = "2011",
month = "12",
day = "1",
doi = "10.1145/2072552.2072555",
language = "English",
isbn = "9781450309882",
series = "MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11",
pages = "7--12",
booktitle = "MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11",

}

Chu, WT, Huang, CC & Cheng, WF 2011, News story clustering from both what and how aspects: Using bag of word model and affinity propagation. in MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11. MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11, pp. 7-12, 2011 ACM Multimedia Conference, MM'11 and Co-Located Workshops - 2011 ACM International Workshop on Automated Media Analysis and Production for Novel TV Services, AIEMPro'11, Scottsdale, AZ, United States, 11-11-28. https://doi.org/10.1145/2072552.2072555

News story clustering from both what and how aspects : Using bag of word model and affinity propagation. / Chu, Wei Ta; Huang, Chao Chin; Cheng, Wen Fang.

MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11. 2011. p. 7-12 (MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11).

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

TY - GEN

T1 - News story clustering from both what and how aspects

T2 - Using bag of word model and affinity propagation

AU - Chu, Wei Ta

AU - Huang, Chao Chin

AU - Cheng, Wen Fang

PY - 2011/12/1

Y1 - 2011/12/1

N2 - The 24-hour news TV channels repeat the same news stories again and again. In this paper we cluster hundreds of news stories broadcasted in a day into dozens of clusters according to topics, and thus facilitate efficient browsing and summarization. The proposed system automatically removes commercial breaks and detects anchorpersons, and then determines boundaries of news stories. Semantic concepts, the bag of visual word model and the bag of trajectory model are used to describe what and how objects present in news stories. After measuring similarity between stories by the earth mover's distance, the affinity propagation algorithm is utilized to cluster stories of the same topic together. The experimental results show that with the proposed methods sophisticated news stories can be effectively clustered.

AB - The 24-hour news TV channels repeat the same news stories again and again. In this paper we cluster hundreds of news stories broadcasted in a day into dozens of clusters according to topics, and thus facilitate efficient browsing and summarization. The proposed system automatically removes commercial breaks and detects anchorpersons, and then determines boundaries of news stories. Semantic concepts, the bag of visual word model and the bag of trajectory model are used to describe what and how objects present in news stories. After measuring similarity between stories by the earth mover's distance, the affinity propagation algorithm is utilized to cluster stories of the same topic together. The experimental results show that with the proposed methods sophisticated news stories can be effectively clustered.

UR - http://www.scopus.com/inward/record.url?scp=84855384891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855384891&partnerID=8YFLogxK

U2 - 10.1145/2072552.2072555

DO - 10.1145/2072552.2072555

M3 - Conference contribution

AN - SCOPUS:84855384891

SN - 9781450309882

T3 - MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11

SP - 7

EP - 12

BT - MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11

ER -

Chu WT, Huang CC, Cheng WF. News story clustering from both what and how aspects: Using bag of word model and affinity propagation. In MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11. 2011. p. 7-12. (MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11). https://doi.org/10.1145/2072552.2072555