CAJ | 학술논문

针对中文微博句子倾向性分类问题，在充分降低由于情感词典的扩充工作带来系统开销的基础上，抽取了中文微博句子中标点符号、情感词权重、词汇级和句法级等新型平面和结构化特征，探索了有效的特征选择方法。在基准COAE和NLP&CC中文微博语料上进行双向交叉和独立实验，并研究了有效的不平衡性语料的处理方法。实验结果表明：采用该文提出的特征后，中文微博句子倾向性分类的性能得到显著提升。
침대중문미박구자경향성분류문제，재충분강저유우정감사전적확충공작대래계통개소적기출상，추취료중문미박구자중표점부호、정감사권중、사회급화구법급등신형평면화결구화특정，탐색료유효적특정선택방법。재기준COAE화NLP&CC중문미박어료상진행쌍향교차화독립실험，병연구료유효적불평형성어료적처리방법。실험결과표명：채용해문제출적특정후，중문미박구자경향성분류적성능득도현저제승。
According to Chinese micro blogging sentence polarity identification problem,while fully reducing due to the emotional lexicon expansion work brought on the basis of system overhead,many novel flat and structural fea-tures,e. g. punctuation,sentiment word weighting,lexical and syntactic level information,from Chinese micro blog-ging,together with the effective feature selection method has been extracted. In-depth bidirectional and independent experiments on both COAE and NLP&CC,along with the effective imbalance corpus handling method has been con-ducted. Evaluation results show that the effectiveness of our novel features. Its also show that the model significantly outperforms existing model currently in the research field.