Context Sentiment Classification Based on Improved Deep Extreme Learning Machine

被引:0
|
作者
Ronghui, Liu [1 ]
Jingpu, Zhang [2 ]
机构
[1] An Associate Professor of the School of Computer and Data Science, Henan University of Urban Construction, Pingdingshan,467036, China
[2] A Lecturer of the School of Computer and Data Science, Henan University of Urban Construction, Pingdingshan,467036, China
来源
IAENG International Journal of Computer Science | 2021年 / 48卷 / 03期
关键词
Deep learning - Learning systems - Convolutional neural networks - Knowledge acquisition - Signal encoding;
D O I
暂无
中图分类号
学科分类号
摘要
In order to improve context sentiment classification accuracy, a sentiment classification algorithm based on deep extreme learning machine with the nearest neighbor and sparse representation (NS-DELM) is presented. Firstly, the extreme learning machine (ELM) is combined with the auto encoder. Secondly, the idea of sparsity and nearest neighbor is integrated into the deep network, and the data integrity is maintained through sparse representation in the projection process. Thirdly, the local manifold structure of the data is maintained by the nearest neighbor representation, and the deep features of the data are extracted layer by layer unsupervised; Finally, the least squares is solved by supervised learning for context sentiment classification. The method is applied to the context sentiment classification experiment of shopping comments. Compared with support vector machine (SVM), stacked auto-encoder (SAE) and convolutional neural network (CNN), the experimental results show that NS-DELM algorithm has higher accuracy than other existing algorithms. © 2021. All Rights Reserved.
引用
收藏
页码:1 / 6
相关论文
共 50 条
  • [31] Deep kernel extreme learning machine classifier based on the improved sparrow search algorithm
    Zhao Guangyuan
    Lei Yu
    The Journal of China Universities of Posts and Telecommunications, 2024, 31 (03) : 15 - 29
  • [32] Deep kernel extreme learning machine classifier based on the improved sparrow search algorithm
    Guangyuan, Zhao
    Yu, Lei
    Journal of China Universities of Posts and Telecommunications, 2024, 31 (03): : 15 - 29
  • [33] A Comparative Evaluation of Traditional Machine Learning and Deep Learning Classification Techniques for Sentiment Analysis
    Dhola, Kaushik
    Saradva, Mann
    2021 11TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING, DATA SCIENCE & ENGINEERING (CONFLUENCE 2021), 2021, : 932 - 936
  • [34] Extreme learning machine based transfer learning for data classification
    Li, Xiaodong
    Mao, Weijie
    Jiang, Wei
    NEUROCOMPUTING, 2016, 174 : 203 - 210
  • [35] Extreme learning machine with kernel model based on deep learning
    Ding, Shifei
    Guo, Lili
    Hou, Yanlu
    NEURAL COMPUTING & APPLICATIONS, 2017, 28 (08): : 1975 - 1984
  • [36] Extreme learning machine with kernel model based on deep learning
    Shifei Ding
    Lili Guo
    Yanlu Hou
    Neural Computing and Applications, 2017, 28 : 1975 - 1984
  • [37] Intelligent Machine Learning with Metaheuristics Based Sentiment Analysis and Classification
    Bhaskaran, R.
    Saravanan, S.
    Kavitha, M.
    Jeyalakshmi, C.
    Kadry, Seifedine
    Rauf, Hafiz Tayyab
    Alkhammash, Reem
    COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 2023, 44 (01): : 235 - 247
  • [38] Machine Learning and Lexicon based Methods for Sentiment Classification: A Survey
    Zhang, Hailong
    Gan, Wenyan
    Jiang, Bo
    2014 11TH WEB INFORMATION SYSTEM AND APPLICATION CONFERENCE (WISA), 2014, : 262 - 265
  • [39] Intelligent Machine Learning with Metaheuristics Based Sentiment Analysis and Classification
    Bhaskaran, R.
    Saravanan, S.
    Kavitha, M.
    Jeyalakshmi, C.
    Kadry, Seifedine
    Rauf, Hafiz Tayyab
    Alkhammash, Reem
    Computer Systems Science and Engineering, 2022, 44 (01): : 235 - 247
  • [40] GENDER CLASSIFICATION BASED ON EVOLUTIONARY EXTREME LEARNING MACHINE
    Li, Xiaodong
    Jiang, Wei
    Mao, Weijie
    Li, Jian
    Chen, Kai
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2013, 9 (09): : 3839 - 3849