基于多任务学习的大五人格预测
Microblog users'Big-Five personality prediction based on multi-task learning
查看参考文献24篇
|
文摘
|
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L_1/L_2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。 |
|
其他语种文摘
|
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 L_1/L_2 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. |
|
来源
|
中国科学院大学学报（中英文）
,2018,35(4):550-560 【核心库】
|
|
DOI
|
10.7523/j.issn.2095-6134.2018.04.019
|
|
关键词
|
新浪微博
;
人格预测
;
多任务学习
;
鲁棒性
;
预测精度
|
|
地址
|
1.
(合肥)电子工程学院, 合肥, 230037
2.
北方电子设备研究所, 北京, 100083
3.
中国科学院心理研究所, 北京, 100101
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
2095-6134 |
|
学科
|
电子技术、通信技术 |
|
基金
|
安徽省部级重大项目
;
国家自然科学基金
|
|
文献收藏号
|
CSCD:6293433
|
参考文献 共
24
共2页
|
|
1.
Goldberg L R. The international personality item pool and future of public-domain personality measures.
Journal of Research in Personality,2006,40(1):84-96
|
CSCD被引
9
次
|
|
|
|
|
2.
Ortigosa A. Predicting user personality by mining social interactions in Facebook.
Journal of Computer and System Sciences,2013,80(1):57-71
|
CSCD被引
7
次
|
|
|
|
|
3.
Wald R. Using Twitter content to predict psychopathy.
Proceedings of the 2012 11th International Conference( ICMLA) on Machine Learning and Applications,2012:394-401
|
CSCD被引
1
次
|
|
|
|
|
4.
Li L. Predicting active users'personality based on micro-blogging behaviors.
Plos One,2014,9(1):e84997
|
CSCD被引
8
次
|
|
|
|
|
5.
Wald R. Machine prediction of personality from Facebook profiles.
Proceedings of the 2012 IEEE 13rd International Conference on Information Reuse and Integration,2012:109-115
|
CSCD被引
1
次
|
|
|
|
|
6.
Bachrach Y. Personality and patterns of Facebook usage.
Proceedings of the 3rd Annual ACM Web Science Conference,2012:24-32
|
CSCD被引
4
次
|
|
|
|
|
7.
Iacobelli F. Large scale personality classification of bloggers.
Fourth International Conference on Affective Computing & Intelligent Interaction,2011:568-577
|
CSCD被引
1
次
|
|
|
|
|
8.
Nowson S. Identifying more bloggers: towards large scale personality classification of personal.
International Conference on Weblogs and Social,2007:1-7
|
CSCD被引
1
次
|
|
|
|
|
9.
Caruana R. Multitask learning.
Machine Learning,1997,28(1):41-75
|
CSCD被引
145
次
|
|
|
|
|
10.
Argyriou A. Convex multi-task feature learning.
Machine Learning,2008,73(3):243-272
|
CSCD被引
40
次
|
|
|
|
|
11.
Ben-David S. A notion of task relatedness yielding provable multiple-task learning guarantees.
Machine Learning,2008,73(3):273-287
|
CSCD被引
5
次
|
|
|
|
|
12.
Zhang Y. Multi-task learning using generalized t process.
Journal of Machine Learning Research Proceedings Track,2010,9(1):964-971
|
CSCD被引
1
次
|
|
|
|
|
13.
Charuvaka A. Classifying protein sequences using regularized multi-task learning.
IEEE/ACM transactions on computational biology and bioinformatics,2014,11(6):1087-1098
|
CSCD被引
2
次
|
|
|
|
|
14.
Zhang J. Learning multiple related tasks latent independent component analysis.
Advances in Neural Information Systems,2006,18:1585-1592
|
CSCD被引
1
次
|
|
|
|
|
15.
Olshausen B A. Emergence of simple-cell receptive field properties by learning a sparse code for natural images.
Nature,1996,381(6583):607-609
|
CSCD被引
238
次
|
|
|
|
|
16.
Mao X. Nonlinear Classification via linear SVMs and multi-task learning.
International Conference on Conference on Information & Knowledge Management,2014:1955-1958
|
CSCD被引
1
次
|
|
|
|
|
17.
白朔天. 多任务回归在社交媒体挖掘中的应用.
哈尔滨工业大学学报,2014,46(9):100-110
|
CSCD被引
4
次
|
|
|
|
|
18.
Evgeniou T. Regularized multi-task learning.
Proceedings of Knowledge Discovery and Data Mining,2004:109-117
|
CSCD被引
1
次
|
|
|
|
|
19.
Yu S. Robust Multi-task Learning with t-Processes.
Proceedings of the 24th International Conference on Machine learning,2007:1103-1110
|
CSCD被引
4
次
|
|
|
|
|
20.
Chen J. Integrating low-rank and group-sparse structures for robust multi-task learning.
Proceedings of the 10th ACM SIGKDD international conference on Knowledge discovery and data mining,2011:42-50
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问