極性反転に対応した評価表現モデル  [in Japanese] Latent Variable Models for Semantic Orientations of Phrases  [in Japanese]

Search this Article

Author(s)

Abstract

複数語から成る評価表現のモデル及びそれに基づいた分類手法を提案する.複数語から成る評価表現の感情極性は, その構成語の感情極性を単純に足し合わせるだけでは算出できないことが多い.そのような表現に対応するために, 我々はモデルに隠れ変数を導入する.実験により, 提案した隠れ変数モデルは複数語から成る評価表現分類において, 82%という高い分類正解率を得ることに成功した.

We propose a model for phrases with semantic orientations as well as a classification method based on the model. Although each phrase consists of multiple words, the semantic orientation of the phrase is not a mere sum of the orientations of the component words. Some words invert the orientation. In order to capture the property of such phrases, we introduce latent variables into the model. Through experiments, we show that the proposed latent variable model works well in the classification of semantic orientations of phrases and achieved nearly 82% classification accuracy.

Journal

  • IPSJ SIG Notes

    IPSJ SIG Notes 168, 141-148, 2005-07-22

    Information Processing Society of Japan (IPSJ)

References:  21

Cited by:  2

Codes

  • NII Article ID (NAID)
    110002952456
  • NII NACSIS-CAT ID (NCID)
    AN10115061
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    09196072
  • NDL Article ID
    7385876
  • NDL Source Classification
    ZM13(科学技術--科学技術一般--データ処理・計算機)
  • NDL Call No.
    Z14-1121
  • Data Source
    CJP  CJPref  NDL  NII-ELS 
Page Top