研究者詳細 - 嶋田　和孝

論文 - 嶋田　和孝

分割表示146 件中 81 - 100 件目／全件表示 >>

Image based Attention Estimation for Interaction Scene 査読有り

Rinko Komiya, Takeshi Saitoh, Kazutaka Shimada

International Conference on ICT Robotics (ICT-ROBOT2017) 2017年11月

The Kyutech corpus and the topic segmentation using a combined method 査読有り

Takashi Yamamura, Kazutaka Shimada and Shintaro Kawahara

Proceedings of the 12th Workshop on Asian Language Resources 95 - 104 2016年12月

Generating abstractive summaries of sports games from Japanese tweets 査読有り

Yuuki Tagawa, Kazutaka Shimada

Proceedings of the 7th International Conference on E-Service and Knowledge Management (ESKM 2016) 2016年07月

Stock market prediction from news on the Web and a new evaluation approach in trading 査読有り

Ko Ichinose, Kazutaka Shimada

Proceedings of the 7th International Conference on E-Service and Knowledge Management (ESKM 2016) 2016年07月

A Sarcasm Extraction Method Based on Patterns of Evaluation Expressions 査読有り

Satoshi Hiai, Kazutaka Shimada

Proceedings of the 7th International Conference on E-Service and Knowledge Management (ESKM 2016) 2016年07月

タブレット端末を用いた議論の合意形成支援システムの開発

桐木平龍之介, 嶋田和孝, Giuseppe Carenini

人工知能学会研究会資料先進的学習科学と工学研究会 ( 一般社団法人人工知能学会 ) 75 ( 0 ) 08 2015年11月

担当区分：最終著者記述言語：日本語掲載種別：研究論文（研究会，シンポジウム資料等）

<p>Problem-based learning (PBL) is one of the most important learning approaches in recent years. In PBL, participants in a group discuss collaboratively to solve a problem and to make a decision through a conversation. In this paper, we propose a tool for supporting consensus-building on multi party conversations. We call it ``Discussion Map''. It consists of nodes and links between them. We divide the nodes into two types; alternatives and criteria. Each criterion contains the importance value. Each link between nodes also contains the importance value. We evaluate the effectiveness of the discussion map system experimentally.</p>

DOI： 10.11517/jsaialst.75.0_08

CiNii Article

CiNii Research

Multi-aspects Rating Prediction Using Aspect Words and Sentences 査読有り

Takuto Nakamuta, Kazutaka Shimada

Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC29) 513 - 521 2015年10月

Trouble information extraction based on a bootstrap approach from Twitter 査読有り

Kohei Kurihara, Kazutaka Shimada

Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC29) 471 - 479 2015年10月

Extractive Summarization Based on a Combined Method Using Several Features for Multi-Party Conversation 査読有り

Yo Tokunaga, Kazutaka Shimada

ACIS International Journal of Computer and Information Science 16 ( 2 ) 12 - 21 2015年10月

On-site likelihood identification of tweets using a two-stage method 査読有り

Kazutaka Shimada, Yurie Onitsuka, Shunsuke Inoue and Tsutomu Endo

Tourism Informatics: Towards novel knowledge based approaches 77 - 90 2015年07月

The effectiveness of time sequence information on a sightseeing spot recommender 査読有り

Kazutaka Shimada, Hisashi Uehara and Tsutomu Endo

Tourism Informatics: Towards novel knowledge based approaches 135 - 150 2015年07月

Trouble information extraction based on a bootstrap approach from Twitter 査読有り

Kurihara K., Shimada K.

29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 471 - 479 2015年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In this paper, we propose a method for ex-Tracting trouble information from Twitter. One useful approach is based on machine learn-ing techniques such as SVMs. However, trou-ble information is a fraction of a percent of all tweets on Twitter. In general, imbalanced distribution is not suitable for machine learn-ing techniques to generate a classifier. An-other approach is to extract trouble informa-Tion by using handwritten rules. However, constructing high coverage rules by handwork is costly. First, we verify these problems in a preliminary experiment. Then, to solve these problems, we apply a bootstrapping method to our trouble information extraction task. We introduce three characteristics and a scoring method to the bootstrapping. As a result, the iteration process on the bootstrapping in-creased the number of tweets and patterns for trouble information dramatically.

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84967214979&origin=inward

Multi-Aspects rating prediction using aspectwords and sentences 査読有り

Nakamuta T., Shimada K.

29th Pacific Asia Conference on Language, Information and Computation, PACLIC 2015 513 - 521 2015年01月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In this paper we propose a method for a rat-ing prediction task. Each review consists of several ratings for a product, namely aspects. To predict the ratings of the aspects, we uti-lize not only aspect words, but also aspect sen-Tences. First, our method detects aspect sen-Tences by using a machine learning technique. Then, it incorporates words extracted from as-pect sentences with aspect word features. For estimating aspect likelihood of each word, we utilize the variance of words among aspects. Finally, it generates classifiers for each aspect by using the extracted features based on the aspect likelihood. Experimental result shows the effectiveness of features from aspect sen-Tences.

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84966908156&origin=inward

Understanding level estimation using discussion maps for supporting consensus-building 査読有り

Hironobu Takagi, Kazutaka Shimada

18th International Conference in Knowledge Based and Intelligent Information and Engineering Systems - KES2014 2014年09月

Multi-party conversation summarization based on sentence selection using verbal and nonverbal information 査読有り

Yo Tokunaga, Kazutaka Shimada

2nd International Conference on Smart Computing and Artificial Intelligence (ICSCAI 2014) 2014年08月

A comparative study of potential-of-interest days on a sightseeing spot recommender 査読有り

Kazutaka Shimada, Hisashi Uehara and Tsutomu Endo

International Workshop on Sustainable Tourism Innovations and Information Systems (STIIS2014) 2014年08月

集合知に基づく観光地推薦システムの構築査読有り

嶋田和孝,上原尚,遠藤勉

観光情報学会「観光と情報」 10 ( 1 ) 113 - 124 2014年06月

Cooperation level estimation of pair work using top-view image 査読有り

Sakaguchi K., Shimada K.

Advances in Intelligent Systems and Computing 272 77 - 87 2014年01月

記述言語：英語掲載種別：研究論文（学術雑誌）

© Springer International Publishing Switzerland 2014.To understand an interaction among persons is one of the most important tasks in artificial intelligence. In this paper, we propose a method for estimating a cooperation level in pair work. The task is a cooperation work that take place in front of a whiteboard by two persons. The goal of our study is to provide the cooperation level that is estimated by features extracted from images for teachers. The result of this study is useful for education support systems and problem based learning. We extract the standing location, operation ratio and head direction of each person from an overhead camera. We apply the features to two machine learning approaches: AdaBooost and multiple linear regression. We obtained 77.5% as the accuracy by the AdaBoost and 0.649 as the adjusted R2 by the regression.

DOI： 10.1007/978-3-319-05570-1_9

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84927761073&origin=inward

Person Identification Using Top-View Image with Depth Information 査読有り

Daichi Kouno, Kazutaka Shimada, Tsutomu Endo

International Journal of Software Innovation 1 ( 2 ) 67 - 79 2013年11月

Conversation summarization using machine learning and scoring method 査読有り

Kazutaka Shimada, Shinpei Toyodome, Tsutomu Endo

Proceedings of the 13th Conference of the Pacific Association for Computational Linguistics 2013年09月

　前のページ - 次のページ　

<嶋田 和孝>

論文 - 嶋田 和孝

<嶋田　和孝>

論文 - 嶋田　和孝