|
|||||
|
|
| 基于卷积记忆网络的视角级微博情感分类* | |
| 引用本文： | 廖祥文,谢媛媛,魏晶晶,桂林,程学旗,陈国龙.基于卷积记忆网络的视角级微博情感分类*[J].模式识别与人工智能,2018,31(3):219-229. |
| 作者姓名： | 廖祥文 谢媛媛 魏晶晶 桂林 程学旗 陈国龙 |
| 作者单位： | 1.福州大学 数学与计算机科学学院 福州 350116 2.福州大学 福建省网络计算与智能信息处理重点实验室 福州 350116 3.福建江夏学院 电子信息科学学院 福州 350108 4.中国科学院网络数据科学与技术重点实验室 北京 100190 |
| 基金项目： | 国家自然科学基金项目(No.U1605251)、中国科学院网络数据科学与技术重点实验室开放基金课题(No.CASNDST201606)、可信分布式计算与服务教育部重点实验室主任基金项目(No.2017KF01)、福建省自然科学基金项目(No. 2017J01755)、赛尔网络下一代互联网技术创新项目(No.NGII20150901)资助 |
| 摘 要： | 现有记忆网络模型中的上下文词之间相互独立,未考虑词序信息对微博情感的影响.因此文中提出基于卷积记忆网络的视角级微博情感分类方法,利用记忆网络可以有效对查询词与文本之间的语义关系进行建模这一特点,将视角与上下文进行抽象处理.通过卷积操作对上下文进行词序拓展,并利用这一结果捕获文中不同词语在上下文中的注意力信号,用于文本的加权表示.在3个公开数据集上的实验表明,相比已有方法,文中方法的正确率和宏F1值效果更好. |
| 关 键 词： | 卷积记忆网络 视角级情感分类 注意力机制 |
| 收稿时间： | 2017-06-03 |
Perspective Level Microblog Sentiment Classification Based on Convolutional Memory Network |
|
| LIAO Xiangwen,XIE Yuanyuan,WEI Jingjing,GUI Lin,CHENG Xueqi,CHEN Guolong.Perspective Level Microblog Sentiment Classification Based on Convolutional Memory Network[J].Pattern Recognition and Artificial Intelligence,2018,31(3):219-229. | |
| Authors: | LIAO Xiangwen XIE Yuanyuan WEI Jingjing GUI Lin CHENG Xueqi CHEN Guolong |
| Affiliation: | 1.College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116 2.Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing,Fuzhou University, Fuzhou 350116 3.College of Electronics and Information Science, Fujian Jiang-xia University, Fuzhou 350108 4.Key Laboratory of Network Data Science and Technology, Chinese Academy of Sciences, Beijing 100190 |
| Abstract: | In the current memory network model, the words of the context are independent of each other, and the influence of word order information on microblog sentiment is not taken into account. Therefore, a perspective level microblog sentiment classification method based on convolutional memory network is proposed. In the method, memory network can effectively model the semantic relation between the query and the text. Consequently, the view and the text are abstracted via this property. Furthermore, the word order in context is extended by convolutional operation. Then, the result is utilized to capture the attention signals of different terms in context for the weighted representation of text. Experimental results on three public datasets indicate that the proposed method achieves higher accuracies and Macro-F1 values compared with other methods. |
| Keywords: | Convolutional Memory Network Perspective Level Sentiment Classification Attention Mechanism |
| 点击此处可从《模式识别与人工智能》浏览原始摘要信息 | |
| 点击此处可从《模式识别与人工智能》下载全文 | |
