Extracting concerns and reports on crimes in blogs

Authors:
Yusuke Abe;Takehito Utsuro;Yasuhide Kawada;Tomohiro Fukuhara;Noriko Kando;Masaharu Yoshioka;Hiroshi Nakagawa;Yoji Kiyota;Masatoshi Tsuchiya
Affiliations:
University of Tsukuba, Tsukuba, Japan;University of Tsukuba, Tsukuba, Japan;Navix Co., Ltd., Tokyo, Japan;National Institute of Advanced Industrial Science and Technology, Tokyo, Japan;National Institute of Informatics, Tokyo, Japan;Hokkaido University, Sapporo, Japan;University of Tokyo, Tokyo, Japan;University of Tokyo, Tokyo, Japan;Toyohashi University of Technology, Toyohashi, Japan
Venue:
AMT'10 Proceedings of the 6th international conference on Active media technology
Year:
2010

Citing 5
Cited 0

Automatically collecting, monitoring, and mining japanese weblogs

Proceedings of the 13th international World Wide Web conference on Alternate track papers & posters
Opinion Analysis Across Languages: An Overview of and Observations from the NTCIR6 Opinion Analysis Pilot Task

WILF '07 Proceedings of the 7th international workshop on Fuzzy Logic and Applications: Applications of Fuzzy Sets Theory
TORISHIKI-KAI, An Autogenerated Web Search Directory

ISUC '08 Proceedings of the 2008 Second International Symposium on Universal Communication
Looking for trouble

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
IR interface for contrasting multiple news sites

AIRS'08 Proceedings of the 4th Asia information retrieval conference on Information retrieval technology

Quantified Score

Hi-index	0.01

Visualization

Abstract

Among other domains and topics on which some issues are frequently argued in the blogosphere, the domain of crime is one of the most seriously discussed by various kinds of bloggers. Such information on crimes in blogs is especially valuable for those who are not familiar with tips for preventing being victimized. This paper proposes a framework of extracting people's concerns and reports on crimes in their own blogs. In this framework, we solve two tasks. In the first task, we focus on experts in crime domain and address the issue of extracting concerns on crimes such as tips for preventing being victimized. In the evaluation of this first task, we show that we successfully rank expert bloggers high in the results of blog feed retrieval. In the second task, on the other hand, we focus on victims of criminal acts, and address the issue of extracting reports on being victimized. In the evaluation of this second task, we show that we outperform blog post ranking based on the search engine API by incorporating dependency relations for identifying victims' blog posts.