Enhanced Quantum Long Short-term Memory Neural Network Based Multi-task Learning for Sentimental Analysis and Cyberbullying Detection

Strategic Insights -

Researchers at Karpagam College of Engineering have made a significant breakthrough in the detection of cyberbullying through the development of a novel deep learning method called Hybrid averaged and weighted averaged review vector Quantum long short-term memory neural based Multitask Learning with Black-winged kite Optimization (HQMLBO). This method uses a combination of natural language processing and machine learning algorithms to effectively identify and classify abusive language. The proposed model was tested on three datasets, including the internet movie database, Yelp polarity, and cyberbullying classification dataset, achieving accuracy rates of 95.68%, 92.5%, and 97.86%, respectively.

Key Takeaways:

  • The novel HQMLBO method combines natural language processing and machine learning algorithms to detect cyberbullying.
  • The proposed model outperforms existing methods in terms of accuracy, with rates of 95.68% for internet movie database, 92.5% for Yelp polarity, and 97.86% for cyberbullying classification dataset.
  • The research concludes that the proposed model is effective in identifying abusive language and reducing cyberbullying.
  • The HQMLBO method uses a hybrid multi-scale with hash vectorization to extract relevant features from the data.
  • The method also employs a hybrid pine cone geyser-inspired optimization algorithm to select the most relevant features.
  • The proposed model achieves significant improvement over existing methods due to its ability to handle large datasets and automatically extract features.

Statistics:

  • 95.68% accuracy rate on the internet movie database dataset.
  • 92.5% accuracy rate on the Yelp polarity dataset.
  • 97.86% accuracy rate on the cyberbullying classification dataset.
  • The proposed method outperforms existing methods in terms of accuracy.
  • The research tested the model on three datasets.

Sources:

  • "Enhanced Quantum Long Short-term Memory Neural Network Based Multi-task Learning for Sentimental Analysis and Cyberbullying Detection" in Expert Systems With Applications, 2025;282.
  • "Karpagam College of Engineering" - K. Subhashree, Dept. of Computer Sciences and Engineering, Coimbatore 641032, Tamil Nadu, India.
  • "NewsRx LLC" - Researchers at Karpagam College of Engineering Report New Data on Networks (Enhanced Quantum Long Short-term Memory Neural Network Based Multi-task Learning for Sentimental Analysis and Cyberbullying Detection). Journal of Engineering. July 7, 2025; p 3981.