I interned at IRIT (Institut de Recherche Informatique de Toulouse) in France as part of a research program. During these two months, I focused on evaluating the effectiveness of jargon extraction algorithms and improving the front end of a platform that utilizes these algorithms.
My primary task was implementing and evaluating the effectiveness of the RAKE (Rapid Automatic Keyword Extraction) and YAKE (Yet Another Keyword Extractor) algorithms in detecting hate speech on social media.
This involved testing and analyzing how well these algorithms could identify and extract key phrases and terms associated with hateful content. The goal was to improve the accuracy and reliability of hate speech detection methods using sample testing, time testing, reliability testing and more...
In addition to implementing and evaluating these algorithms, I worked on improving the front end of the platform that uses them. The objective was to make the platform more user-friendly, especially for novice users.
Full Details and References :