Optimizing Knowledge Discovery in Big Data Using NLP Techniques

SCOPE:

The rapid proliferation of web-based information, combined with the advent of novel data sources and data collection methods, has led to a rapid growth in text mining research. Techniques and methodologies initially developed within the realm of information retrieval have found application in a wide array of challenges, spanning document classification, clustering, link analysis, and concept discovery. Within this expansive landscape, the domain of information extraction and knowledge discovery in text mining has witnessed remarkable growth over the past decade, underscoring its paramount significance.

Information Extraction, a domain of artificial intelligence research is preoccupied with the automated extraction of insights from textual content. While closely related with Natural Language Processing (NLP), it frequently necessitates more advanced approaches for the identification and categorization of concepts. The primary objective is to unearth valuable information concealed within unstructured text such as news articles or web pages, information that may not be explicitly catalogued in other databases or information repositories. This scope extends to diverse fields, encompassing product catalogues, medical diagnostic reports, log entries from scientific instruments, user query logs detailing their interactions with e-commerce platform, personalized recommendations delivered by social networks, and many others. Information Extraction and Knowledge Discovery in big data emerge as the two preeminent machine learning methodologies for processing textual data. Nevertheless, despite the extensive research in these domains, numerous challenges persist before they can be effectively harnessed in practical scenarios. The field of information extraction and knowledge discovery has indeed made significant strides over the past decade; however, attaining precision remains a formidable obstacle. Key challenges encompass the scarcity of adequate data resources, the disconnect between low-level features and high-level semantic relationships, the limited availability of human-generated training data, and a growing body of evidence advocating for more intricate Part-of-Speech (POS) tagging methods necessitating an expansive array of training patterns. Nevertheless, this research domain continues to exert a profound impact on our daily lives through a multitude of applications.

This special issue is centred around "Optimizing Knowledge Discovery in Big Data Using NLP Techniques" Our primary objective is to collect a collection of high-quality papers broadly categorized into Information Extraction, Sentiment Analysis and Opinion Mining Applications with emphasis on real-world applications and their consequential effects. We welcome submissions encompassing both theoretical frameworks and empirical investigations of data-driven methodologies tailored to extract knowledge from corpus-level text data.

TOPICS:

  • Enhancing Big Data Knowledge Extraction through Advanced NLP Algorithms.
  • Privacy-Preserving Techniques for Knowledge Discovery in Big Data using NLP.
  • Cross-Lingual Knowledge Discovery in Multilingual Big Data with NLP.
  • Sentiment Analysis for Knowledge Extraction in Big Data with NLP.
  • Real-time Knowledge Discovery in Big Data Streams using NLP.
  • Explainable AI Approaches for Knowledge Extraction from Big Data
  • Semantic Enrichment of Big Data for Improved Knowledge Discovery using NLP.
  • Knowledge Graphs and Ontologies for Structured Big Data Knowledge Extraction with NLP.
  • Deep Learning Models for Knowledge Discovery in Unstructured Big Data
  • Contextual Understanding and Inference in Big Data Knowledge Extraction with NLP.
  • Human-in-the-Loop Approaches for Validating Knowledge Discovery in Big Data via NLP.
  • Multimodal Fusion for Enhanced Knowledge Extraction from Big Data
  • Ethical Considerations in Big Data Knowledge Discovery using NLP Techniques

IMPORTANT DATES:

  • Manuscript submission deadline: 15 March 2024
  • Notification of acceptance: 15 June 2024
  • Submission of final revised paper: 15 September 2024
  • Publication of special issue (tentative): 15, December 2024

GUEST EDITORS: