DEIM Forum 2009 A4-4 305-8573 1-1-1 305-8573 1-1-1 277-8568 5-1-5 Wikipedia API Wikipedia Wikipedia Semi-Automatic Discovery of Cross-Cultural Gaps through Japanese/English Blog Distillation Hiroyuki NAKASAKI,MarikoKAWABA, Sayuri YAMAZAKI,TakehitoUTSURO,and Tomohiro FUKUHARA Grad. Sch. Systems and Information Engineering, University of Tsukuba, Tsukuba, 305-8573, Japan College of Eng. Sys., Third Cluster of Colleges, University of Tsukuba, Tsukuba, 305-8573, Japan Research into Artifacts, Center for Engineering, University of Tokyo Kashiwa, Chiba 277-8568, Japan Abstract The goal of this paper is to cross-lingually analyze multilingual blogs collected with a topic keyword. The framework of collecting multilingual blogs with a topic keyword is designed as the blog feed retrieval procedure. Multilingual queries for retrieving blog feeds are created from Wikipedia entries. Finally, we cross-lingually and cross-culturally compare less well known facts and opinions that are closely related to a given topic. Preliminary evaluation results support the effectiveness of the proposed framework. Key words blog, topic analysis, cultural gaps, Wikipedia, cross-lingual IR 1. Technorati 1 BlogPulse 2 kizasi.jp 3 blogwatcher 4 Globe of Blogs 5 1 http://technorati.com/ 2 http://www.blogpulse.com/ 3 http://kizasi.jp/ 4 http://blogwatcher.pi.titech.ac.jp/ 5 http://www.globeofblogs.com/
Best Blogs in Asia Directory 6 Blogwise 7 Wikipedia API Wikipedia [1] [3] 1 Wikipedia Wikipedia Wikipedia 2. Wikipedia 50 Wikipedia 1 3. 3. 1 Wikipedia 6 http://www.misohoni.com/bba/ 7 http://www.blogwise.com/ 2 [1] 2 ( 10) Yahoo!Japan API Yahoo! API 11 8 12 9 3. 2 Wikipedia Wikipedia Wikipedia Wikipedia 2 3. 3 8 FC2.com yahoo.co.jp rakuten.ne.jp ameblo.jp goo.ne.jp livedoor.jp Seesaa.net jugem.jp yaplog.jp webry.info.jp hatena.ne.jp 9 blogspot.com msnblogs.net spaces.live.com livejournal.com vox.com multiply.com typepad.com aol.com blogsome.com wordpress.com blog-king.net blogster.com
1 1 ( ) ( ) Whaling Organ transplant Tobacco smoking Subprime lending X J P J(X J) Y E P E(Y E) X J P J (X J )= Y E P E(Y E)=
2 (/ ) Wikipedia Wikipedia / 162 / 174 121 / 239 2232 / 6532 5024966 / 2611942 100 / 231 89 / 206 696 / 1301 995927 / 781476 399 / 276 86 / 252 1481 / 400 1323767 / 492727 39 / 68 134 / 205 1088 / 1216 980552 / 883450 Wikipedia Wikipedia 10 X J X J X E R J(X J,X E) Y E Y E Y J R E(Y E,Y J) PJ (XJ ) PE(YE) R J (X J,X E)= RE(YE,YJ )= P E(X E) P J (Y J ) 3 3 3. 5 3. 4 3. 2 Wikipedia PostScore(p) = (weight(type(t)) freq(t)) t weight(type(t)) Wikipedia t type(t) freq(t) p Wikipedia t Wikipedia t type(t) 3 2 0.5 PostScore(p) SiteScore(s) = PostScore(p) p p s SiteScore(s) 10 http://www.eijiro.jp/ 10 4 5 3. 5 3 Wikipedia 300 4 X J ( R J(X J,X E),P J(X J)) X J X E X E (R E(X E,X J),P E(X E)) X E X J
3 (a) (b) (c) (d) 4. [4] [5] 5. Wikipedia
4 10 () / / / / Whaling ( ) 1 3 5 6 8 / () 1 / ( ) 1 3 4 5 10 / () 2 / 30 ( ) 4 / () 6 / 12 ( ) 6 / () 3 / ( ) 7 9 / () 4 / ( ) 8 / () 10 / 1 Organ transplant ( ) 2 3 4 6 9 / () 1 / ( ) 2 6 / () 8 / ( ) 7 / () 14 / ( ) 3 / () 2 / ( ) 8 10 / () 7 / ( ) 8 / () 7 / 5 10 ( ) / / / / Tobacco smoking ( ) 1 / () 7 / ( ) 2 / () 6 / ( ) 2 5 10 / () 10 / ( ) 5 / () 1 / ( ) 9 / () 14 / ( ) 9 / () 9 / Subprime lending ( ) 1 4 6 9 / () 2 / ( ) 1 4 / () 3 / ( ) 3 / () 17 / ( ) 3 / () 1 / ( ) 10 / () 18 / ( ) 5 / () 19 / [1],,,. Wikipedia. 19 6 (DEWS2008), 2008. [2],,,. Wikipedia. 22, 2008. [3],,,. Wikipedia., Vol. 2008, No. (2008 NL 187), pp. 83 90, 2008. [4],,.. 13 Web, pp. 40 43, 2007. [5].. 13 Web, pp. 27 20, 2007.
(a) (b) URL 3
(a) / Whaling (b) / Air guitar 4