RSS Feeds Filtering from multiple sources using automated techniques of Natural Language Processing

Authors

  • Mujeeb-ur-Rehman Jamali Emaan Institute of Management and Sciences, Karachi Pakistan
  • Najma Imtiaz Ali The University of Sindh Jamshoro, Pakistan.
  • Mujeeb-u-Rehman Maree Maree The University of Sindh Jamshoro, Pakistan.
  • Akhtar Hussain Soomro The Government College University Hyderabad, Pakistan.
  • Safeeullah Soomro American National University and University of FairFax USA.
  • Abdul Ghafoor Memon Emaan Institute of Management and Sciences, Karachi Pakistan.

DOI:

https://doi.org/10.62019/abbdm.v4i1.118

Abstract

The Internet's rapid growth has resulted in a surge of information, posing challenges for users trying to stay updated. The World Wide Web, with its diverse websites updated at varying intervals, necessitates efficient categorization of news articles. As the number of online news sources continues to rise, categorization becomes crucial for users to find information easily. Given the overwhelming volume of digital media information, categorizing news using algorithms and assigning multiple tags based on their category becomes essential. In the modern digital era, users face difficulties filtering and accessing relevant content tailored to their preferences due to the abundance of information from various sources. This study employs Natural Language Processing (NLP) methods for automated content filtering of RSS feeds. The developed system extracts feeds via RSS, generates headings and summaries, and employs NLP for categorization. This research has broad implications, offering opportunities for improved information management, personalized recommendations, and informed decision-making across diverse domains.

Downloads

Published

2024-03-19

How to Cite

Jamali, M.- ur-R., Ali, N. I., Maree, M.- u-R. M., Soomro, A. H., Soomro, S., & Memon, A. G. (2024). RSS Feeds Filtering from multiple sources using automated techniques of Natural Language Processing . The Asian Bulletin of Big Data Management, 4(1). https://doi.org/10.62019/abbdm.v4i1.118