| 講演名 | 2016-05-12 [Encouragement Talk] A Novel Approach for Multi-Class Sentiment Analysis in Twitter Mondher Bouazizi(慶大), Tomoaki Ohtsuki(慶大), |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | Many works were conducted on the automatic sentiment analysis and opinion mining. However, most of these works were oriented towards the classification of texts into positive and negative. In this report, we propose a pattern-based approach that goes deeper in the classification of texts collected from Twitter (i.e., tweets) and classifies the tweets into 7 different classes. Experiments show that our approach reaches an accuracy of classification equal to 56.9% and a precision level of sentimental tweets (other than neutral and sarcastic) equal to 72.6%. Nevertheless, the approach proves to be very accurate in binary classification (i.e., classification into ?positive? and ?negative?) and ternary classification (i.e., classification into ?positive?, ?negative? and ?neutral?): in the former case, we reach an accuracy of 87.5% for the same dataset used after removing neutral tweets, and in the latter case, we reached an accuracy of classification of 83.0%. |
| 抄録(英) | Many works were conducted on the automatic sentiment analysis and opinion mining. However, most of these works were oriented towards the classification of texts into positive and negative. In this report, we propose a pattern-based approach that goes deeper in the classification of texts collected from Twitter (i.e., tweets) and classifies the tweets into 7 different classes. Experiments show that our approach reaches an accuracy of classification equal to 56.9% and a precision level of sentimental tweets (other than neutral and sarcastic) equal to 72.6%. Nevertheless, the approach proves to be very accurate in binary classification (i.e., classification into ?positive? and ?negative?) and ternary classification (i.e., classification into ?positive?, ?negative? and ?neutral?): in the former case, we reach an accuracy of 87.5% for the same dataset used after removing neutral tweets, and in the latter case, we reached an accuracy of classification of 83.0%. |
| キーワード(和) | Twitter / sentiment analysis / opinion mining |
| キーワード(英) | Twitter / sentiment analysis / opinion mining |
| 資料番号 | ASN2016-3 |
| 発行日 | 2016-05-05 (ASN) |
| 研究会情報 | |
| 研究会 | ASN |
|---|---|
| 開催期間 | 2016/5/12(から2日開催) |
| 開催地（和） | 構造計画研究所 本所新館 |
| 開催地（英） | |
| テーマ（和） | 知的環境, センサネットワーク, スマート建築, スマートシティ, 構造モニタリング, ゼロエネルギービルディング, 社会基盤センシング, BIM/CIM, 国土基盤モデル, 一般, 建築学会・スマート建築モニタリング応用小委員会後援, 土木学会・土木情報学委員会後援 |
| テーマ（英） | |
| 委員長氏名（和） | 東條 弘(NTT) |
| 委員長氏名（英） | Hiroshi Tohjo(NTT) |
| 副委員長氏名（和） | 関屋 大雄(千葉大) / 岡田 啓(名大) / 吉原 貴仁(KDDI研) |
| 副委員長氏名（英） | Hiroo Sekiya(Chiba Univ.) / Hiraku Okada(Nagoya Univ.) / Kiyohito Yoshihara(KDDI R&D Labs.) |
| 幹事氏名（和） | 塩川 茂樹(神奈川工科大) / 清水 芳孝(NTT) |
| 幹事氏名（英） | Shigeki Shiokawa(Kanagawa Inst. of Tech.) / Yoshitaka Shimiza(NTT) |
| 幹事補佐氏名（和） | 五十嵐 悠一(日立) / 内藤 克浩(愛知工大) / 服部 聖彦(NICT) / 藤田 裕志(富士通研) / 米澤 拓郎(慶大) |
| 幹事補佐氏名（英） | Yuichi Igarashi(Hitachi) / Katsuhiro Naito(Aichi Inst. of Tech.) / Kiyohiko Hattori(NICT) / Hiroshi Fujita(Fujitsu Labs.) / Takuro Yonezawa(Keio Univ.) |
| 講演論文情報詳細 | |
| 申込み研究会 | Technical Committee on Ambient intelligence and Sensor Networks |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | [Encouragement Talk] A Novel Approach for Multi-Class Sentiment Analysis in Twitter |
| サブタイトル（和） | |
| キーワード(1)（和/英） | Twitter / Twitter |
| キーワード(2)（和/英） | sentiment analysis / sentiment analysis |
| キーワード(3)（和/英） | opinion mining / opinion mining |
| 第 1 著者 氏名（和/英） | Mondher Bouazizi / Mondher Bouazizi |
| 第 1 著者 所属（和/英） | Keio University(略称：慶大) Keio University(略称：Keio Univ.) |
| 第 2 著者 氏名（和/英） | Tomoaki Ohtsuki / Tomoaki Ohtsuki |
| 第 2 著者 所属（和/英） | Keio University(略称：慶大) Keio University(略称：Keio Univ.) |
| 発表年月日 | 2016-05-12 |
| 資料番号 | ASN2016-3 |
| 巻番号（vol） | vol.116 |
| 号番号（no） | ASN-22 |
| ページ範囲 | pp.13-18(ASN), |
| ページ数 | 6 |
| 発行日 | 2016-05-05 (ASN) |