Presentation 2014-06-14
On-site likelihood identification of tweets with context information
Yurie ONITSUKA, Kazutaka SHIMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Web contains much information for the tourism, such as impressions and sentiments about sightseeing areas. Analyzing the information is a significant task for tourism informatics. A useful target resource for the analysis is information on Twitter. However, all tweets with keywords, which are related to facilities and events for tourism, might be not tourism information. In this paper, we propose a method for estimating on-site likelihood of tweets. The task is to identify whether each tweet has high on-site likelihood. We introduce a filtering process and a machine learning technique for the task. In addition, we apply previous and next tweets for the identification task, as context information. Experimental results show the effectiveness of the combination method and context information.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Twitter / Context / On-site likelihood
Paper # NLC2014-5
Date of Issue

Conference Information
Committee NLC
Conference Date 2014/6/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On-site likelihood identification of tweets with context information
Sub Title (in English)
Keyword(1) Twitter
Keyword(2) Context
Keyword(3) On-site likelihood
1st Author's Name Yurie ONITSUKA
1st Author's Affiliation Department of Artificial Intelligence, Kyushu Institute of Technology()
2nd Author's Name Kazutaka SHIMADA
2nd Author's Affiliation Department of Artificial Intelligence, Kyushu Institute of Technology
Date 2014-06-14
Paper # NLC2014-5
Volume (vol) vol.114
Number (no) 81
Page pp.pp.-
#Pages 6
Date of Issue