Relationship analysis between user's contexts and real input words through Twitter

Yutaka Arakawa, Shigeaki Tagashira, Akira Fukuda

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

4 被引用数 (Scopus)

抄録

In this paper, we propose a method to evaluate effectiveness of our proposed context-aware text entry by using Twitter. We focus on "geo-tagged" public tweets because they include user's important contexts, real location and time. We also focus on TV program listing because 50% traffic of iPhone in Japan is generated from our home, in which I often tweets in watching a TV. Cyclical collecting system based on Streaming API and Search API of Twitter is proposed for gathering the target tweets efficiently. In order to find the relationship between user's contexts and really used words, we compare really-tweeted words with words obtained from Local Search API of Yahoo! Japan that is used for our context-aware text entry and words obtained from TV program listing. We analyze 471274 tweets that have been collected from 15 December 2009 to 10 June 2010 for specifying the relationship to landmark information and TV program. As a result, we show that 5.1% of tweets include landmark words, and 9% of tweets include TV program words. Additionally, we bring out that there are location dependent words and time dependent words.

本文言語英語
ホスト出版物のタイトル2010 IEEE Globecom Workshops, GC'10
出版社IEEE Computer Society
ページ1751-1755
ページ数5
ISBN(印刷版)9781424488650
DOI
出版ステータス出版済み - 2010
イベント2010 IEEE Globecom Workshops, GC 2010 - Miami, 米国
継続期間: 12月 5 201012月 10 2010

出版物シリーズ

名前2010 IEEE Globecom Workshops, GC'10

会議

会議2010 IEEE Globecom Workshops, GC 2010
国/地域米国
CityMiami
Period12/5/1012/10/10

!!!All Science Journal Classification (ASJC) codes

  • コンピュータ ネットワークおよび通信
  • 通信

フィンガープリント

「Relationship analysis between user's contexts and real input words through Twitter」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル