The project crawls data from different Urdu news web sites to identify similar news and generate a tag cloud. The project was challenging due to unavailability of text processing libraries in Urdu language. We developed Urdu processing engine/libraries to do the text mining task. This news website has different categories and news realting to that website coming on that categories. Once an event occurs relating to that category than that category instantly update. Newslink.pk has different famous news tag and each tag has news list relating to that tag.
CATEGORY: php | scala
DATE:January 10, 2023