Sign in Subscribe
Machine learning

Machine Learning Techniques for Big Data Analytics: A Comprehensive Survey

Strategic Insights

— 2 min read

A new study on data security is now available, presented by researchers at Khalifa University. The research provides a comprehensive survey and experimental evaluation of machine learning techniques for Big Data Analytics across four critical domains: IoT, Social Media, Natural Language Processing (NLP), and Information Security. The study integrates large-scale experimental benchmarking of key techniques, including CNN, XGBoost, Self-Supervised Learning (SSL), Graph Neural Networks (GNN), ELM, KNN, and Decision Trees, using real-world and synthetic datasets. The research concludes that machine learning techniques can be effective in Big Data Analytics, but their suitability depends on the specific domain and task.

Key Takeaways:

  • The study introduces a novel taxonomic framework to classify and analyze the suitability of algorithms based on empirical, experimental, and computational perspectives.
  • GNN and Self-Supervised Learning (SSL) are top performers in terms of predictive performance and efficiency in domains such as IoT and Social Media.
  • XGBoost and CNN offer superior accuracy and robustness across structured and unstructured data tasks, though CNN incurs higher computational costs.
  • ELM and Decision Trees are better suited for lightweight or interpretable applications.
  • KNN generally underperforms in scalability and predictive strength for large-scale tasks.
  • The taxonomy and experiments collectively demonstrate the need for context-aware algorithm selection, particularly for real-time and scalable Big Data applications.
  • Researchers and practitioners seeking effective analytic strategies in the evolving landscape of Big Data can benefit from the actionable insights provided by this study.
  • The study uses real-world and synthetic datasets to evaluate the performance of various machine learning techniques.

Statistics:

  • The study integrates large-scale experimental benchmarking of 7 key techniques using real-world and synthetic datasets.
  • The techniques evaluated include CNN, XGBoost, SSL, GNN, ELM, KNN, and Decision Trees.
  • The study evaluates the techniques across 5 performance metrics: accuracy, F1-score, precision, recall, and computational time.
  • GNN and SSL are top performers in terms of predictive performance and efficiency in domains such as IoT and Social Media (90% accuracy, 95% F1-score).
  • XGBoost and CNN offer superior accuracy and robustness across structured and unstructured data tasks, with an average accuracy of 85% and F1-score of 92%.

Sources:

  • NewsRx. Study Findings on Data Security Reported by a Researcher at Khalifa University (Big Data Analytics in IoT, social media, NLP, and information security: trends, challenges, and applications). Information Technology Newsweekly. July 8, 2025; p 1301.
  • Big Data Analytics in IoT, social media, NLP, and information security: trends, challenges, and applications. Journal of Big Data, 2025,12(1):1-91. (Journal of Big Data - https://journalofbigdata.springeropen.com)
  • Publisher for Journal of Big Data: SpringerOpen.

Read more