OPT OpenIR  > 光学影像学习与分析中心
Identifying Objective and Subjective Words via Topic Modeling
Wang, Hanqi1; Wu, Fei1; Lu, Weiming1; Yang, Yi2; Li, Xi1; Li, Xuelong3; Zhuang, Yueting1
Department光学影像学习与分析中心
2018-03-01
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN2162-237X
Volume29Issue:3Pages:718-730
Contribution Rank3
Abstract

It is observed that distinct words in a given document have either strong or weak ability in delivering facts (i.e., the objective sense) or expressing opinions (i.e., the subjective sense) depending on the topics they associate with. Motivated by the intuitive assumption that different words have varying degree of discriminative power in delivering the objective sense or the subjective sense with respect to their assigned topics, a model named as identified objective-subjective latent Dirichlet allocation (LDA) (iosLDA) is proposed in this paper. In the iosLDA model, the simple Polya urn model adopted in traditional topic models is modified by incorporating it with a probabilistic generative process, in which the novel "Bag-of-DiscriminativeWords" (BoDW) representation for the documents is obtained; each document has two different BoDW representations with regard to objective and subjective senses, respectively, which are employed in the joint objective and subjective classification instead of the traditional Bag-of-Topics representation. The experiments reported on documents and images demonstrate that: 1) the BoDW representation is more predictive than the traditional ones; 2) iosLDA boosts the performance of topic modeling via the joint discovery of latent topics and the different objective and subjective power hidden in every word; and 3) iosLDA has lower computational complexity than supervised LDA, especially under an increasing number of topics.

KeywordLatent Dirichlet Allocation (Lda) Latent Variable Model Supervised Learning Topic Modeling
Subject AreaComputer Science, Artificial Intelligence
DOI10.1109/TNNLS.2016.2626379
Indexed BySCI ; EI
Language英语
WOS IDWOS:000426344600018
EI Accession Number20170403279564
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30754
Collection光学影像学习与分析中心
Corresponding AuthorWu, Fei
Affiliation1.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou 310027, Peoples R China;
2.Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Ultimo, NSW 2007, Australia;
3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr Opt IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Wang, Hanqi,Wu, Fei,Lu, Weiming,et al. Identifying Objective and Subjective Words via Topic Modeling[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(3):718-730.
APA Wang, Hanqi.,Wu, Fei.,Lu, Weiming.,Yang, Yi.,Li, Xi.,...&Zhuang, Yueting.(2018).Identifying Objective and Subjective Words via Topic Modeling.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(3),718-730.
MLA Wang, Hanqi,et al."Identifying Objective and Subjective Words via Topic Modeling".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.3(2018):718-730.
Files in This Item:
File Name/Size DocType Version Access License
Identifying Objectiv(4246KB)期刊论文出版稿开放获取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
[Wang, Hanqi]'s Articles
[Wu, Fei]'s Articles
[Lu, Weiming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Hanqi]'s Articles
[Wu, Fei]'s Articles
[Lu, Weiming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Hanqi]'s Articles
[Wu, Fei]'s Articles
[Lu, Weiming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Identifying Objective and Subjective Words via Topic Modeling.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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