Data sparsity for twitter sentiment analysis in real-time from biased and noisy data

被引:1
|
作者
Rawal, Richa [1 ]
Bandil, Devesh Kumar [1 ]
Nath, Srawan [1 ]
机构
[1] Suresh Gyan Vihar Univ, Dept Comp Sci & Engn, Jaipur, Rajasthan, India
关键词
Mathematical modeling; Ordinary differential equations; A duopoly economy; Market share; KEY DISTRIBUTION PROTOCOL; BLACK-HOLE; DESIGN;
D O I
10.1080/09720529.2021.2020420
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
Specializing in the analysis of strong emotions expressed in text, sentiment analysis is a scientific field. You may convey your thoughts and feelings about anything by expressing your opinion about it. This work explains the origins of sentiment analysis and how to configure sentiment evaluators. This paper showed comprehensive assessment of emotions will still be required. Analysis includes non-textual material. The use of visual media in social research is also useful. Without a doubt, I see the value of these links. This research uses a domain-specific seed list to categorize tweets. As much information as possible is preserved during tweet categorization. The algorithm categorizes tweets precisely and sentimentally to build a user interest profile. To test the method, 1 million tweets were used and up to 96% of them were correctly classified.
引用
收藏
页码:2403 / 2413
页数:11
相关论文
共 50 条
  • [31] Exploring Sentiment Analysis on Twitter Data
    Venugopalan, Manju
    Gupta, Deepa
    [J]. 2015 EIGHTH INTERNATIONAL CONFERENCE ON CONTEMPORARY COMPUTING (IC3), 2015, : 241 - 247
  • [32] Real-Time Data ETL Framework for Big Real-Time Data Analysis
    Li, Xiaofang
    Mao, Yingchi
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION, 2015, : 1289 - 1294
  • [33] Using Custom Fuzzy Thesaurus to Incorporate Semantics and Reduce Data Sparsity for Twitter Sentiment Analysis
    Ismail, Heba M.
    Zaki, Nazar
    Belkhouche, Boumediene
    [J]. 2016 3RD INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE (ISCMI 2016), 2016, : 47 - 52
  • [34] Real-time algorithms for estimating jerk signals from noisy acceleration data
    Nakazawa, S
    Ishihara, T
    Inooka, H
    [J]. INTERNATIONAL JOURNAL OF APPLIED ELECTROMAGNETICS AND MECHANICS, 2003, 18 (1-3) : 149 - 163
  • [35] Online real-time learning of dynamical systems from noisy streaming data
    S. Sinha
    S. P. Nandanoori
    D. A. Barajas-Solano
    [J]. Scientific Reports, 13
  • [36] Online real-time learning of dynamical systems from noisy streaming data
    Sinha, S.
    Nandanoori, S. P.
    Barajas-Solano, D. A.
    [J]. SCIENTIFIC REPORTS, 2023, 13 (01)
  • [37] A spark-based big data analysis framework for real-time sentiment prediction on streaming data
    Kilinc, Deniz
    [J]. SOFTWARE-PRACTICE & EXPERIENCE, 2019, 49 (09): : 1352 - 1364
  • [38] Real-time traffic event detection using Twitter data
    Jones, Angelica Salas
    Georgakis, Panagiotis
    Petalas, Yannis
    Suresh, Renukappa
    [J]. INFRASTRUCTURE ASSET MANAGEMENT, 2018, 5 (03) : 77 - 84
  • [39] DESIGN AND EVALUATION OF AN ARTEFACT FOR REAL-TIME TWITTER SENTIMENT ANALYSIS: LESSONS LEARNT
    Van der Linde, I
    Kotze, E.
    [J]. JOURNAL FOR NEW GENERATION SCIENCES, 2018, 16 (01) : 129 - 144
  • [40] Real-time Twitter Sentiment Analysis using 3-way classifier
    Al Shammari, Alaa S.
    [J]. 2018 21ST SAUDI COMPUTER SOCIETY NATIONAL COMPUTER CONFERENCE (NCC), 2018,