PSYCH OpenIR  > 社会与工程心理学研究室
基于多任务学习的大五人格预测
Alternative TitleMicroblog users’Big-Five personality prediction based on multi-task learning
郑敬华1; 郭世泽2; 高梁2; 赵楠3
First Author郑敬华
2018
Source Publication中国科学院大学学报
Correspondent Emailzhengjh1001@163. com
ISSN2095-6134
Subtype期刊论文
Volume35Issue:4Pages:550-560
Contribution Rank3
Abstract

传统的社交网络用户的人格预测方法是采用单任务分类或回归的机器学习方法,这类方法忽略多个任务之间的潜在关联信息,并且在小规模训练数据条件下很难取得较好的预测效果。提出基于鲁棒多任务学习模型对微博用户进行大五人格的预测,既共享多个任务之间的关联信息,又能够识别出不相关任务。参数矩阵也相应地被分解为结构项和异常项,采用核范数和L1/L2范数进行正则项约束,将问题转化为求解优化问题。通过真实的新浪微博用户数据进行方法有效性的验证,5个维度的平均正确率、平均精确率和平均召回率分别达到67.3%、71.5%和74.6%,同时与在相同数据集上采取传统的单任务学习方法和多任务学习方法进行比较,结果表明本文提出的基于鲁棒多任务学习方法的预测效果优于其他几种方法。

Other Abstract

Most of traditional prediction methods of social network users’personality are based on single-task classification or regression machine learning. They ignore the potential related information between multiple tasks,and are very difficult to get admirable prediction results based on small scale training data. In this paper,a robust multi-task learning method ( RMTL) is proposed to predict Big-Five personality of Microblog users,and it can not only share the task relations,but also identify irrelevant ( outlier) tasks. The model is first decomposed into two components,i. e. ,a structure and an outlier,and then the nucleus norm and L1 /L2 norm are used to constrain the regular term so as to solve the optimization problems. With Sina Microblog users’data,we validate the RMTL method,and the average correct rate,average precision rate,and average recall rate of the five dimensions are 67. 3%,71. 5%,and 74. 6%,respectively. The RMTL method outperforms the 4 single-task learning methods and the multi-task learning.

Keyword新浪微博 人格预测 多任务学习 鲁棒性 预测精度
Indexed ByCSCD
Language中文
CSCD IDCSCD:6293433
Citation statistics
Document Type期刊论文
Identifierhttp://ir.psych.ac.cn/handle/311026/27048
Collection社会与工程心理学研究室
Affiliation1.电子工程学院
2.北方电子设备研究所
3.中国科学院心理研究所
Recommended Citation
GB/T 7714
郑敬华,郭世泽,高梁,等. 基于多任务学习的大五人格预测[J]. 中国科学院大学学报,2018,35(4):550-560.
APA 郑敬华,郭世泽,高梁,&赵楠.(2018).基于多任务学习的大五人格预测.中国科学院大学学报,35(4),550-560.
MLA 郑敬华,et al."基于多任务学习的大五人格预测".中国科学院大学学报 35.4(2018):550-560.
Files in This Item:
File Name/Size DocType Version Access License
基于多任务学习的大五人格预测_郑敬华.p(641KB)期刊论文出版稿限制开放CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[郑敬华]'s Articles
[郭世泽]'s Articles
[高梁]'s Articles
Baidu academic
Similar articles in Baidu academic
[郑敬华]'s Articles
[郭世泽]'s Articles
[高梁]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[郑敬华]'s Articles
[郭世泽]'s Articles
[高梁]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于多任务学习的大五人格预测_郑敬华.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.