| Tri-Training for authorship attribution with limited training data: a comprehensive study |
| Qian, TY; Liu, B; Chen, L; Peng, ZY; Zhong, M; He, GL; Li, XH; Xu, G
|
| 2016
|
| 发表期刊 | NEUROCOMPUTING
 |
| ISSN | 0925-2312
|
| 卷号 | 171页码:798-806 |
| 摘要 | Authorship attribution (AA) aims to identify the authors of a set of documents. Traditional studies in this area often assume that there are a large set of labeled documents available for training. However, in the real life, it is often difficult or expensive to collect a large set of labeled data. For example, in the online review domain, most reviewers (authors) only write a few reviews, which are not enough to serve as the training data for accurate classification. In this paper, we present a novel three-view Tri-Training method to iteratively identify authors of unlabeled data to augment the training set. The key idea is to first represent each document in three distinct views, and then perform Tri-Training to exploit the large amount of unlabeled documents. Starting from 10 training documents per author, we systematically evaluate the effectiveness of the proposed Tri-Training method for AA. Experimental results show that the proposed approach outperforms the state-of-the-art semi-supervised method CNG-FSVM and other baselines. (C) 2015 Elsevier B.V. All rights reserved.; Authorship attribution (AA) aims to identify the authors of a set of documents. Traditional studies in this area often assume that there are a large set of labeled documents available for training. However, in the real life, it is often difficult or expensive to collect a large set of labeled data. For example, in the online review domain, most reviewers (authors) only write a few reviews, which are not enough to serve as the training data for accurate classification. In this paper, we present a novel three-view Tri-Training method to iteratively identify authors of unlabeled data to augment the training set. The key idea is to first represent each document in three distinct views, and then perform Tri-Training to exploit the large amount of unlabeled documents. Starting from 10 training documents per author, we systematically evaluate the effectiveness of the proposed Tri-Training method for AA. Experimental results show that the proposed approach outperforms the state-of-the-art semi-supervised method CNG-FSVM and other baselines. (C) 2015 Elsevier B.V. All rights reserved. |
| 收录类别 | SCI
|
| 关键词 | Authorship Attribution
Tri-training
Limited Training Data
|
| 部门归属 | Wuhan Univ, State Key Lab Software Engn, Wuhan 430072, Peoples R China. Univ Illinois, Chicago, IL 60607 USA. Chinese Acad Sci, Inst Software, Beijing 100190, Peoples R China.
|
| 语种 | 英语
|
| WOS记录号 | WOS:000364883900080
|
| 引用统计 |
|
| 内容类型 | 期刊论文
|
| URI标识 | http://ir.iscas.ac.cn/handle/311060/17416
|
| 专题 | 中国科学院软件研究所
|
推荐引用方式
GB/T 7714 |
Qian, TY,Liu, B,Chen, L,et al. Tri-Training for authorship attribution with limited training data: a comprehensive study[J]. NEUROCOMPUTING,2016,171:798-806.
|
| APA |
Qian, TY.,Liu, B.,Chen, L.,Peng, ZY.,Zhong, M.,...&Xu, G.(2016).Tri-Training for authorship attribution with limited training data: a comprehensive study.NEUROCOMPUTING,171,798-806.
|
| MLA |
Qian, TY,et al."Tri-Training for authorship attribution with limited training data: a comprehensive study".NEUROCOMPUTING 171(2016):798-806.
|
修改评论