Exploring the role of named entities for uncertainty recognition in event detection

Masnizah Mohd, Kiyoaki Shirai

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

Abstract

Ambiguous information contributes to the uncertainty issue. Type of information such as using named entities has been proved to provide significant information to the user compared to the 'bag-of-words' in identifying an event. So what else could contribute to the uncertainty in an event detection? We propose to answer this question by analysing the distribution of named entities across topics, and explore the potential of named entities in a user experiment. We construct an event detection task with 20 users and use news dataset from Topic Detection and Tracking (TDT) corpus, under the Sports and Politics categories. We analyse the results from five uncertainty dimensions: too little information, too much information, complex information, ambiguous information and conflicting information. These dimensions are categorise as two factors; amount and type of information. There was no statistical significance difference in the amount of information given with the number of successful event detected. However, with little information and high named entities has contributes in reducing uncertainty. In addition, the amount of information and information quality are mutually independent. Our results suggest that uncertainty vary substantially between the amount of information and type of information in event detection.

Original languageEnglish
Title of host publicationKMIS
PublisherSciTePress
Pages335-341
Number of pages7
Volume3
ISBN (Electronic)9789897581588
Publication statusPublished - 2015
Externally publishedYes
Event7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015 - Lisbon, Portugal
Duration: 12 Nov 201514 Nov 2015

Other

Other7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015
CountryPortugal
CityLisbon
Period12/11/1514/11/15

Fingerprint

Sports
Uncertainty
Experiments

Keywords

  • Event detection
  • Named entities
  • Uncertainty
  • User

ASJC Scopus subject areas

  • Software

Cite this

Mohd, M., & Shirai, K. (2015). Exploring the role of named entities for uncertainty recognition in event detection. In KMIS (Vol. 3, pp. 335-341). SciTePress.

Exploring the role of named entities for uncertainty recognition in event detection. / Mohd, Masnizah; Shirai, Kiyoaki.

KMIS. Vol. 3 SciTePress, 2015. p. 335-341.

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

Mohd, M & Shirai, K 2015, Exploring the role of named entities for uncertainty recognition in event detection. in KMIS. vol. 3, SciTePress, pp. 335-341, 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2015, Lisbon, Portugal, 12/11/15.
Mohd, Masnizah ; Shirai, Kiyoaki. / Exploring the role of named entities for uncertainty recognition in event detection. KMIS. Vol. 3 SciTePress, 2015. pp. 335-341
@inproceedings{352f50abbef7409488fa945eec7d38f8,
title = "Exploring the role of named entities for uncertainty recognition in event detection",
abstract = "Ambiguous information contributes to the uncertainty issue. Type of information such as using named entities has been proved to provide significant information to the user compared to the 'bag-of-words' in identifying an event. So what else could contribute to the uncertainty in an event detection? We propose to answer this question by analysing the distribution of named entities across topics, and explore the potential of named entities in a user experiment. We construct an event detection task with 20 users and use news dataset from Topic Detection and Tracking (TDT) corpus, under the Sports and Politics categories. We analyse the results from five uncertainty dimensions: too little information, too much information, complex information, ambiguous information and conflicting information. These dimensions are categorise as two factors; amount and type of information. There was no statistical significance difference in the amount of information given with the number of successful event detected. However, with little information and high named entities has contributes in reducing uncertainty. In addition, the amount of information and information quality are mutually independent. Our results suggest that uncertainty vary substantially between the amount of information and type of information in event detection.",
keywords = "Event detection, Named entities, Uncertainty, User",
author = "Masnizah Mohd and Kiyoaki Shirai",
year = "2015",
language = "English",
volume = "3",
pages = "335--341",
booktitle = "KMIS",
publisher = "SciTePress",

}

TY - GEN

T1 - Exploring the role of named entities for uncertainty recognition in event detection

AU - Mohd, Masnizah

AU - Shirai, Kiyoaki

PY - 2015

Y1 - 2015

N2 - Ambiguous information contributes to the uncertainty issue. Type of information such as using named entities has been proved to provide significant information to the user compared to the 'bag-of-words' in identifying an event. So what else could contribute to the uncertainty in an event detection? We propose to answer this question by analysing the distribution of named entities across topics, and explore the potential of named entities in a user experiment. We construct an event detection task with 20 users and use news dataset from Topic Detection and Tracking (TDT) corpus, under the Sports and Politics categories. We analyse the results from five uncertainty dimensions: too little information, too much information, complex information, ambiguous information and conflicting information. These dimensions are categorise as two factors; amount and type of information. There was no statistical significance difference in the amount of information given with the number of successful event detected. However, with little information and high named entities has contributes in reducing uncertainty. In addition, the amount of information and information quality are mutually independent. Our results suggest that uncertainty vary substantially between the amount of information and type of information in event detection.

AB - Ambiguous information contributes to the uncertainty issue. Type of information such as using named entities has been proved to provide significant information to the user compared to the 'bag-of-words' in identifying an event. So what else could contribute to the uncertainty in an event detection? We propose to answer this question by analysing the distribution of named entities across topics, and explore the potential of named entities in a user experiment. We construct an event detection task with 20 users and use news dataset from Topic Detection and Tracking (TDT) corpus, under the Sports and Politics categories. We analyse the results from five uncertainty dimensions: too little information, too much information, complex information, ambiguous information and conflicting information. These dimensions are categorise as two factors; amount and type of information. There was no statistical significance difference in the amount of information given with the number of successful event detected. However, with little information and high named entities has contributes in reducing uncertainty. In addition, the amount of information and information quality are mutually independent. Our results suggest that uncertainty vary substantially between the amount of information and type of information in event detection.

KW - Event detection

KW - Named entities

KW - Uncertainty

KW - User

UR - http://www.scopus.com/inward/record.url?scp=84960954088&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960954088&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 335

EP - 341

BT - KMIS

PB - SciTePress

ER -