中国邮电高校学报(英文) ›› 2009, Vol. 16 ›› Issue (1): 106-110.doi: 10.1016/S1005-8885(08)60188-0

• Artificial Intelligence • 上一篇    下一篇

Words semantic orientation classification based on HowNet

李钝,MA Yong-tao, GUO Jian-li   

  1. School of Information Engineering, Zhengzhou University, Zhengzhou 450001, China
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-02-26
  • 通讯作者: 李钝

Words semantic orientation classification based on HowNet

LI Dun, MA Yong-tao, GUO Jian-li   

  1. School of Information Engineering, Zhengzhou University, Zhengzhou 450001, China
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-02-26
  • Contact: LI Dun

摘要:

Based on the text orientation classification, a new measurement approach to semantic orientation of words was proposed. According to the integrated and detailed definition of words in HowNet, seed sets including the words with intense orientations were built up. The orientation similarity between the seed words and the given word was then calculated using the sentiment weight priority to recognize the semantic orientation of common words. Finally, the words’ semantic orientation and the context were combined to recognize the given words’ orientation. The experiments show that the measurement approach achieves better results for common words’ orientation classification and contributes particularly to the text orientation classification of large granularities.

关键词:

text;classification,;semantic;orientation,;semantic;similarity,;orientation;weight;priority,;HowNet

Abstract:

Based on the text orientation classification, a new measurement approach to semantic orientation of words was proposed. According to the integrated and detailed definition of words in HowNet, seed sets including the words with intense orientations were built up. The orientation similarity between the seed words and the given word was then calculated using the sentiment weight priority to recognize the semantic orientation of common words. Finally, the words’ semantic orientation and the context were combined to recognize the given words’ orientation. The experiments show that the measurement approach achieves better results for common words’ orientation classification and contributes particularly to the text orientation classification of large granularities.

Key words:

text classification;semantic orientation;semantic similarity;orientation weight priority;HowNet