DEIM Forum 2010 A Web Abstract Classification Method for Revie

Similar documents
DEIM Forum 2010 A3-3 Web Web Web Web Web. Web Abstract Web-page R

Microsoft Word - toyoshima-deim2011.doc

1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,

IPSJ SIG Technical Report Vol.2009-DBS-149 No /11/ Bow-tie SCC Inter Keyword Navigation based on Degree-constrained Co-Occurrence Graph

SERPWatcher SERPWatcher SERP Watcher SERP Watcher,

IPSJ SIG Technical Report Vol.2011-EC-19 No /3/ ,.,., Peg-Scope Viewer,,.,,,,. Utilization of Watching Logs for Support of Multi-

Wikipedia 2 Wikipedia Web Wikipedia 2. Web [6] [11] [8] 2 SVM Bollegala [1] 5-gram URL URL 2-gram [6] [11] SVM 3 SVM [8] Bollegala [1] SVM [7] [9] [6]

IT,, i

DEIM Forum 2009 E

1 Web [2] Web [3] [4] [5], [6] [7] [8] S.W. [9] 3. MeetingShelf Web MeetingShelf MeetingShelf (1) (2) (3) (4) (5) Web MeetingShelf

1: ( 1) 3 : 1 2 4

Web [1] [2] [3] [4] [5] SupportVectorMachine SVM [6] [7] Google [11] Web

. Yahoo! 1!goo 2 QA..... QA Web Web [1]Web Web Yin [2] Web Web Web. [3] Web Wikipedia 1 2

TF-IDF TDF-IDF TDF-IDF Extracting Impression of Sightseeing Spots from Blogs for Supporting Selection of Spots to Visit in Travel Sat

DEIM Forum 2009 B4-6, Str

main.dvi

main.dvi


IPSJ SIG Technical Report Vol.2014-CE-126 No /10/11 1,a) Kinect Support System for Romaji Learning through Exercise Abstract: Educatio

7,, i

IPSJ SIG Technical Report Vol.2010-SLDM-144 No.50 Vol.2010-EMB-16 No.50 Vol.2010-MBL-53 No.50 Vol.2010-UBI-25 No /3/27 Twitter IME Twitte

Web Web Web Web Web, i

ICT Web Web ICT Web 2. 新 学 習 指 導 要 領 の 理 念 と 教 育 の 情 報 化 の 意 義 2-1 新 学 習 指 導 要 領 の 理 念 ICT 2

DEIM Forum 2009 C8-4 QA NTT QA QA QA 2 QA Abstract Questions Recomme

09_加藤_紀要_2007

1: A/B/C/D Fig. 1 Modeling Based on Difference in Agitation Method artisoc[7] A D 2017 Information Processing

1 7.35% 74.0% linefeed point c 200 Information Processing Society of Japan

日本感性工学会論文誌

IPSJ SIG Technical Report Vol.2012-CG-148 No /8/29 3DCG 1,a) On rigid body animation taking into account the 3D computer graphics came

(MIRU2008) HOG Histograms of Oriented Gradients (HOG)

3D UbiCode (Ubiquitous+Code) RFID ResBe (Remote entertainment space Behavior evaluation) 2 UbiCode Fig. 2 UbiCode 2. UbiCode 2. 1 UbiCode UbiCode 2. 2

Vol.55 No (Jan. 2014) saccess 6 saccess 7 saccess 2. [3] p.33 * B (A) (B) (C) (D) (E) (F) *1 [3], [4] Web PDF a m

1 1 tf-idf tf-idf i

[2] OCR [3], [4] [5] [6] [4], [7] [8], [9] 1 [10] Fig. 1 Current arrangement and size of ruby. 2 Fig. 2 Typography combined with printing

untitled

知能と情報, Vol.30, No.5, pp

H19国際学研究科_02.indd


IPSJ SIG Technical Report An Evaluation Method for the Degree of Strain of an Action Scene Mao Kuroda, 1 Takeshi Takai 1 and Takashi Matsuyama 1

22 Google Trends Estimation of Stock Dealing Timing using Google Trends

( )

17 Proposal of an Algorithm of Image Extraction and Research on Improvement of a Man-machine Interface of Food Intake Measuring System

3_39.dvi

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2

IPSJ SIG Technical Report Vol.2011-MUS-91 No /7/ , 3 1 Design and Implementation on a System for Learning Songs by Presenting Musical St

大学における原価計算教育の現状と課題

日大_新聞学研究科パンフ.indd

, IT.,.,..,.. i

BOK body of knowledge, BOK BOK BOK 1 CC2001 computing curricula 2001 [1] BOK IT BOK 2008 ITBOK [2] social infomatics SI BOK BOK BOK WikiBOK BO

The copyright of this material is retained by the Information Processing Society of Japan (IPSJ). The material has been made available on the website

..,,,, , ( ) 3.,., 3.,., 500, 233.,, 3,,.,, i

THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.

IPSJ SIG Technical Report Secret Tap Secret Tap Secret Flick 1 An Examination of Icon-based User Authentication Method Using Flick Input for

Sobel Canny i

untitled

人工知能学会研究会資料 SIG-KBS-B Analysis of Voting Behavior in One Night Werewolf 1 2 Ema Nishizaki 1 Tomonobu Ozaki Graduate School of Integrated B

Input image Initialize variables Loop for period of oscillation Update height map Make shade image Change property of image Output image Change time L

23 A Comparison of Flick and Ring Document Scrolling in Touch-based Mobile Phones

Microsoft Word - deim2011_new-ichinose doc


1 4 4 [3] SNS 5 SNS , ,000 [2] c 2013 Information Processing Society of Japan

,,, Twitter,,, ( ), 2. [1],,, ( ),,.,, Sungho Jeon [2], Twitter 4 URL, SVM,, , , URL F., SVM,, 4 SVM, F,.,,,,, [3], 1 [2] Step Entered

& Vol.2 No (Mar. 2012) 1,a) , Bluetooth A Health Management Service by Cell Phones and Its Us

Table 1 Table 2

01-譴カ蜴・-8.fm

2 : Open Clip Art Library [4] Microsoft Office PowerPoint Web PowerPoint 2 Yahoo! Web [5] SlideShare Yahoo! Web Yahoo! Web

24 Region-Based Image Retrieval using Fuzzy Clustering

Vol.54 No (July 2013) [9] [10] [11] [12], [13] 1 Fig. 1 Flowchart of the proposed system. c 2013 Information

IPSJ SIG Technical Report Vol.2009-HCI-134 No /7/17 1. RDB Wiki Wiki RDB SQL Wiki Wiki RDB Wiki RDB Wiki A Wiki System Enhanced by Visibl

36

Q [4] 2. [3] [5] ϵ- Q Q CO CO [4] Q Q [1] i = X ln n i + C (1) n i i n n i i i n i = n X i i C exploration exploitation [4] Q Q Q ϵ 1 ϵ 3. [3] [5] [4]

本文.indd

29 jjencode JavaScript

The 18th Game Programming Workshop ,a) 1,b) 1,c) 2,d) 1,e) 1,f) Adapting One-Player Mahjong Players to Four-Player Mahjong

& Vol.5 No (Oct. 2015) TV 1,2,a) , Augmented TV TV AR Augmented Reality 3DCG TV Estimation of TV Screen Position and Ro

: Name, Tel name tel (! ) name : Name! Tel tel ( % ) 3. HTML. : Name % Tel name tel 2. 2,., [ ]!, [ ]!, [ ]!,. [! [, ]! ]!,,. ( [ ], ),. : [Name], nam

untitled

Vol. 42 No. SIG 8(TOD 10) July HTML 100 Development of Authoring and Delivery System for Synchronized Contents and Experiment on High Spe

情報処理学会研究報告 IPSJ SIG Technical Report Vol.2011-MBL-57 No.27 Vol.2011-UBI-29 No /3/ A Consideration of Features for Fatigue Es

kut-paper-template.dvi

Web Stamps 96 KJ Stamps Web Vol 8, No 1, 2004

e-learning e e e e e-learning 2 Web e-leaning e 4 GP 4 e-learning e-learning e-learning e LMS LMS Internet Navigware

h1_h4.eps

[2] , [3] 2. 2 [4] 2. 3 BABOK BABOK(Business Analysis Body of Knowledge) BABOK IIBA(International Institute of Business Analysis) BABOK 7

DPA,, ShareLog 3) 4) 2.2 Strino Strino STRain-based user Interface with tacticle of elastic Natural ObjectsStrino 1 Strino ) PC Log-Log (2007 6)


,,,,., C Java,,.,,.,., ,,.,, i

(a) 1 (b) 3. Gilbert Pernicka[2] Treibitz Schechner[3] Narasimhan [4] Kim [5] Nayar [6] [7][8][9] 2. X X X [10] [11] L L t L s L = L t + L s

100 SDAM SDAM Windows2000/XP 4) SDAM TIN ESDA K G G GWR SDAM GUI

2reN-A14.dvi

1 2 3 ( ) ( ) SNS SNS Facebook %[g]( %[ ]) [ ] IT LNS (Life Networking Service) LNS LNS LNS SNS SNS 3. LNS (Life Networking S

HP cafe HP of A A B of C C Map on N th Floor coupon A cafe coupon B Poster A Poster A Poster B Poster B Case 1 Show HP of each company on a user scree

Elmore & Pohlmann Greenwood & Ramagli a b c a b c

3.1 Thalmic Lab Myo * Bluetooth PC Myo 8 RMS RMS t RMS(t) i (i = 1, 2,, 8) 8 SVM libsvm *2 ν-svm 1 Myo 2 8 RMS 3.2 Myo (Root

独立行政法人情報通信研究機構 Development of the Information Analysis System WISDOM KIDAWARA Yutaka NICT Knowledge Clustered Group researched and developed the infor

28 Horizontal angle correction using straight line detection in an equirectangular image

Hansen 1 2, Skinner 5, Augustinus 6, Harvey 7 Windle 8 Pels 9 1 Skinner 5 Augustinus 6 Pels 9 NL Harvey ML 11 NL

Web Hashtag Hashtag Twitter Hashtag Twitter Hashtag Hashtag Hashtag Twitter Hashtag Twitter Hashtag contexthashtag contexthashtag Hashtag contexthasht

[1] [3]. SQL SELECT GENERATE< media >< T F E > GENERATE. < media > HTML PDF < T F E > Target Form Expression ( ), 3.. (,). : Name, Tel name tel

熊本大学学術リポジトリ Kumamoto University Repositor Title 特別支援を要する児童生徒を対象としたタブレット端末 における操作ボタンの最適寸法 Author(s) 竹財, 大輝 ; 塚本, 光夫 Citation 日本産業技術教育学会九州支部論文集, 23: 61-

Transcription:

DEIM Forum 2010 A2-2 305 8550 1 2 305 8550 1 2 E-mail: s0813158@u.tsukuba.ac.jp, satoh@slis.tsukuba.ac.jp Web Abstract Classification Method for Reviews using Degree of Mentioning each Viewpoint Tomoya ARAI and Tetsuji SATOH School of Library and Information Science, University of Tsukuba 1 2, Kasuga, Tsukuba, Ibaraki, 305 8550 Japan Graduate School of Library, Information and Media Studies, University of Tsukuba 1 2, Kasuga, Tsukuba, Ibaraki, 305 8550 Japan E-mail: s0813158@u.tsukuba.ac.jp, satoh@slis.tsukuba.ac.jp Online reputation is the quite useful information for both product choice and marketing research. The volume of reputation information is continuously increasing. As a result, the user must seek much reputation information to get the useful information. This is a burden very much for a user. In this paper, we propose an approach to classify opinion sentences in either of plural evaluation viewpoints. In this approach, we make related terms dictionary with a related degree for each evaluation viewpoint and we calculate a reference degree every evaluation viewpoint of a sentence with the dictionary. We realize the classification of the opinion sentence with the reference degree. Through comparing proposed approach with SVM, we confirm that precision improved by the proposed approach. Key words Reputation information, classification, Information retrieval, Evaluation viewpoint, Reference degree 1. web.com 1 2 1 http://kakaku.com/ 2 http://travel.rakuten.co.jp/ 1

1.com 3 PC 1 1 1 1 8 PC PC 1 2 3 http://review.kakaku.com/ 3 2 3 4 5 6 7 2. [1] 2. 1 Hu [2] [3] Hu 2

2. 2 [4] [5] [6] [7] 3 PC 1 2 2 1 3 2 3 3 2. 3 3 2 2 3. 3. 2 3. 1 3. 2. 1 3

2 MeCab 4 <,,,*><,,*,*> < > < > 1 1 3. 2. 2 ( ) 2 R w(v j) = log ( S v j S w S v j ) 1 n i=1 S v i S w n i=1 S v i R w(v j) v j w S v j S w v j w i 1 < = i < = n n v j w w 4 http://mecab.sourceforge.net/ (1) 1 3. 3 3. 3. 1, 4

3. 3. 2 3. 3. 1 0 0 0 4..com.com.com PC.com.com Java.com.com PC TV 2 5. 4. N SVM PC 4. PC 8 PC 2009 7 17 3000 1220 3 A : B : 3000 C : 603 3 1 A B C 1 35341 36561 603 5. 1 N N 10% 20% 100% V P V = (2) V V R V = (3) V P V V R V V 3 V 2 3 5

(a) 精度と再現率 (a) 精度と再現率 (b) F 値と再現率 (b) F 値と再現率 図 3 辞書 A を使った分類の結果 図4 辞書 B を使った分類の結果 で正解判定し 正しく分類された文の数である 上位 N 位の精 度と再現率は システムが評価視点 V に分類した文数を 上位 N 位までに分類された文の数として求めた 図 3(a) は辞書 A 図 4(a) は辞書 B 図 5(a) は辞書 C を使っ てテストデータを分類した精度と再現率を示す 図の横軸は再 現率 縦軸は精度であり グラフは評価視点ごとの分類結果で ある 再現率が 1 に届かない理由として 意見文が正しい評価視点 に分類されず他の評価視点に分類されたからである 例えば デザインが良いです という文が 処理速度 の評価視点に 分類された場合 評価視点 デザイン のところでは再現率が (a) 精度と再現率 低下する 図 5(a) は図 3(a) や図 4(a) のグラフと比べて評価視点ごとに 精度と再現率が大きく異なっている これは評価視点の語を含 む文の抽出した数が影響している 本手法では辞書を作成する 際に評価視点の語を含む文を抽出し その抽出した文を使って 関連語と関連度を求めている そのため 抽出する文の数が少 ないと 関連語の数が少なくなり 関連度は文の集合全体での 出現回数や評価視点の語と共起する回数が 1 回違うだけで大き く変わる 図 5(a) の 使いやすさ の精度と再現率は 再現率 の向上とともに精度も向上している部分や 精度が極端に低下 している部分がある これは 大きな関連度を持つ 1 語によっ (b) F 値と再現率 て言及度がほぼ決定されてしまい その語が正解文に出現する 確率による影響を受けているためである 図 5 辞書 C を使った分類の結果 6

5. 2 SVM SVM Lib- SVM 5 RBF multiclass 2 C 603 PC 8 + 9 5. 1 3(b) 4(b) 5(b) F 2 SVM 1220 603 3 SVM 3 SVM A 4.9% B 6.9% 603 C 1.9% 3 % A 72.7 B 74.7 C 65.7 SVM 67.8 5 http://www.csie.ntu.edu.tw/ cjlin/libsvm/ 4 16.38 15.68 13.73 15cm 12.39 11.07 10.40 PC 10.38 9.19 PHOTSHOP iphone 8.96 8.23 5. 3 PC 8 9.com 10 4 8 1220 4 PC 6. 75% SVM 7% 3 603 SVM 2% 1 7

2 6 1 2 3.com 2 3 [1],... pp. 201-241. 2006 [2] Minqing Hu and Bing Liu. Mining aminqing Hu and Bing Liu. Mining and summarizingcustomer reviews. In Proceedings of the Tenth ACMSIGKDD International Conference on Knowledge Discoveryand Data Mining, pp. 168-177, 2004. [3],,.. 11 C2-9. 2005. [4],,,,,,. Web. 2004-FI-076, Vol. 2004, No. 93, pp. 1-8, 2004. [5],,,,.. 16 (DEWS2006), 2C-i10. 2006. [6],.. 19 (DEWS2009), 6C-5. 2009. [7],.. Web (WebDB Forum2009), 1B-1. 2009. 7. SVM 75%SVM 7% 700g 8