一種改進EM算法的跨領(lǐng)域情感分類方法
發(fā)布時間：2018-07-17 17:30
【摘要】：監(jiān)督學習算法是當前進行文本情感分類的主要方法,往往要求訓練集與測試集的數(shù)據(jù)分布相同,然而在實際情況下已標注數(shù)據(jù)與測試數(shù)據(jù)常常不屬于同一個領(lǐng)域,這種數(shù)據(jù)分布差異導致文本情感分類準確率下降。針對這一問題,提出了一種基于EM算法的跨領(lǐng)域情感分類方法。首先從多個源領(lǐng)域結(jié)合目標領(lǐng)域生成一個情感傾向參考表;其次利用改進的EM算法參考該表迭代調(diào)節(jié)目標領(lǐng)域分類器的分類結(jié)果,直到該結(jié)果可以與參考表匹配;最后在公開數(shù)據(jù)集上與貝葉斯、SVM等主流分類方法進行對比實驗。實驗結(jié)果表明,該方法在一定程度上提高了跨領(lǐng)域情感分類的準確性。
[Abstract]:Supervised learning algorithm is the main method of text emotion classification. It often requires the same data distribution between the training set and the test set. However, in practice, the labeled data and the test data often do not belong to the same field. The difference in data distribution results in a decrease in the accuracy of text affective classification. To solve this problem, a cross-domain emotion classification method based on EM algorithm is proposed. First, an emotional preference reference table is generated from multiple source fields combined with target fields; secondly, the improved EM algorithm is used to iteratively adjust the classification results of the target domain classifier until the result can be matched with the reference table. Finally, a comparison experiment is carried out on the open data set with Bayesian SVM and other mainstream classification methods. Experimental results show that this method improves the accuracy of cross-domain emotion classification to some extent.
【作者單位】： 國家數(shù)字交換系統(tǒng)工程技術(shù)研究中心;
【基金】：國家科技支撐計劃資助項目(2014BAH30B01) 國家自然科學基金創(chuàng)新群體資助項目(61521003);國家自然科學基金資助項目(61379151)
【分類號】：TP391.1
本文編號：2130411
[Abstract]:Supervised learning algorithm is the main method of text emotion classification. It often requires the same data distribution between the training set and the test set. However, in practice, the labeled data and the test data often do not belong to the same field. The difference in data distribution results in a decrease in the accuracy of text affective classification. To solve this problem, a cross-domain emotion classification method based on EM algorithm is proposed. First, an emotional preference reference table is generated from multiple source fields combined with target fields; secondly, the improved EM algorithm is used to iteratively adjust the classification results of the target domain classifier until the result can be matched with the reference table. Finally, a comparison experiment is carried out on the open data set with Bayesian SVM and other mainstream classification methods. Experimental results show that this method improves the accuracy of cross-domain emotion classification to some extent.
【作者單位】： 國家數(shù)字交換系統(tǒng)工程技術(shù)研究中心;
【基金】：國家科技支撐計劃資助項目(2014BAH30B01) 國家自然科學基金創(chuàng)新群體資助項目(61521003);國家自然科學基金資助項目(61379151)
【分類號】：TP391.1
【相似文獻】
相關(guān)期刊論文 前8條
1 孟勃;朱明;;采用EM算法對粒子濾波跟蹤算法進行改進[J];中國圖象圖形學報;2009年09期
2 李玉玲;;基于邊界齊次方列聯(lián)表棱向量的EM算法[J];中國科技信息;2010年10期
3 王學軍;李智勇;王亮亮;;基于自適應EM算法的光學圖像海域分割[J];無線電工程;2011年04期
4 龍興明,周靜;基于EM算法的圖像小波系數(shù)統(tǒng)計研究[J];計算機仿真;2005年06期
5 于林森;張?zhí)镂?;用于圖像分割的濾波EM算法[J];計算機學報;2006年06期
6 趙佳;何小海;陶青川;劉瑩;;基于深度變化成像模型的調(diào)整EM算法[J];光學技術(shù);2006年03期
7 安永輝;;EM算法的研究及其在文本處理中的應用[J];現(xiàn)代計算機;2013年10期
8 張德喜;黃浩;;一種適合于大數(shù)據(jù)集處理的混合EM算法[J];計算機應用;2006年08期
相關(guān)碩士學位論文 前2條
1 董寶玉;XCT中錐束投影重排算法與EM算法的研究[D];大連理工大學;2005年
2 景麗俊;基于聚類和關(guān)聯(lián)規(guī)則的名醫(yī)臨證思維及方藥應用規(guī)律挖掘方法[D];暨南大學;2011年
，本文編號：2130411
本文鏈接：http://www.sikaile.net/kejilunwen/ruanjiangongchenglunwen/2130411.html
最近更新
教材專著
