计算机工程 ›› 2012, Vol. 38 ›› Issue (9): 183-185.doi: 10.3969/j.issn.1000-3428.2012.09.055

• 人工智能及识别技术 • 上一篇    下一篇

基于维吾尔语情感词的句子情感分析

黄 俊1a,田生伟2,禹 龙1b,冯冠军1c   

  1. (1. 新疆大学 a. 信息科学与工程学院;b. 网络中心;c. 人文学院,乌鲁木齐 830046;2. 新疆大学软件学院,乌鲁木齐 830008)
  • 收稿日期:2011-06-29 出版日期:2012-05-05 发布日期:2012-05-05
  • 作者简介:黄 俊(1987-),男,硕士研究生,主研方向:人工智能;田生伟,副教授、博士;禹 龙,副教授;冯冠军,副教授、博士
  • 基金项目:
    国家自然科学基金资助项目(60963017);国家社会科学基金资助项目(10BTQ045, 11XTQ007);新疆大学博士基金资助项目(BS100120)

Sentence Sentiment Analysis Based on Uyghur Sentiment Word

HUANG Jun 1a, TIAN Sheng-wei 2, YU Long 1b, FENG Guan-jun 1c   

  1. (a. Institute of Information Science and Engineering; b. Net Center; c. College of Humanities, Xinjiang University, Urumqi 830046, China; 2. School of Software, Xinjiang University, Urumqi 830008, China)
  • Received:2011-06-29 Online:2012-05-05 Published:2012-05-05

摘要: 提出基于自动标注的维吾尔语情感词分析句子情感的方法。将8种情感类别作为情感类别集合。判断句子中是否含有转折性连词,若有则屏蔽含有转折性连词句子的前半部分,通过条件随机场模型自动标注句子中的情感词,依据标注的情感词,为句子的每种情感类别打分,得分最高的情感类型作为句子的候选情感。识别句中维语的否定成分,根据否定成分出现的奇偶次数对句子的候选情感修正,得到句子的最终情感类型。实验结果表明,在句子情感分析上该方法可取得较好的效果。

关键词: 维吾尔语, 条件随机场模型, 特征模板, 情感词, 否定成分, 句子情感

Abstract: This paper proposes the mechanism of sentence sentiment identification based on sentiment tagged word level constituents acquired by an automatic classifier. Basic set of eight sentiment types is selected for the test. The first part of the sentence is shielded if the sentence contains adversative conjunction. Conditional Random Field(CRF) model is used to tag the words with the sentiment types automatically, and referring to the words of automatic tagging, giving a score to each sentiment type of a sentence. The highest score of sentiment type is chosen to candidate sentiment type. According to the number of negative components in sentences is oven or odd, and the final sentiment type of sentence is revised. Experimental results show that the method on sentence sentiment analysis achieves good effect.

Key words: uyghur, Conditional Random Field(CRF) model, feature template, sentiment word, negative component, sentence sentiment

中图分类号: