A solution for the synonym problem in word frequency algorithms

Abstract

This thesis’s goal is to present an algorithm that serves to augment the regular word frequency algorithms by introducing and incorporating the synonyms of the words in the process of counting frequencies. The thesis consists of three parts that serve to inform the reader about why this change could be an improvement, provide a description of the technologies used in the project as well as an in-depth explanation of the algorithm that was built and finally its application to real world data along with the analysis of the results.