Structured Poi data extraction from internet news

Hua Ping Zhang*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

POI (Point of Interest) database is key resources for GIS (Geographic Information System) application. POI manual gathering is expensive and time consuming. This paper presents a state-of-the-art solution that automatically extracts structured POI data from Internet news. The procedure includes making lexical analysis news Internet, and then identifying time expression, location and organization entities, extracting an event scenario based on POI heuristic features. With POI data extraction, consistency between event and entity, result optimization and filtering with heuristics was taken into account. Open testing with experiment conducted on 1,000 news, the precision is 93.60% and recall is 75.48%. The method within POI oriented event extraction is effective and has been applied in industrial POI collection.

Original languageEnglish
Title of host publication2010 4th International Universal Communication Symposium, IUCS 2010 - Proceedings
Pages116-122
Number of pages7
DOIs
Publication statusPublished - 2010
Event2010 4th International Universal Communication Symposium, IUCS 2010 - Beijing, China
Duration: 18 Oct 201019 Oct 2010

Publication series

Name2010 4th International Universal Communication Symposium, IUCS 2010 - Proceedings

Conference

Conference2010 4th International Universal Communication Symposium, IUCS 2010
Country/TerritoryChina
CityBeijing
Period18/10/1019/10/10

Fingerprint

Dive into the research topics of 'Structured Poi data extraction from internet news'. Together they form a unique fingerprint.

Cite this