A Survey Report on Hypernym Techniques for Text Classification

Abstract

In this digital world, social media has become a communication platform for the entire world. It allows the users to express their views and opinions on various platforms. During this process, both structured and unstructured data is collected in a random manner. The exclusion of categorization causes the user to have difficulty in understanding or accessing information relating to those categories that they like. In the field of social network analysis, the automation procedure for inferring special interests from users is a challenging task. The solution for this is classification of text which inherently classifies with natural language against certain categories on text. Feature Expansion is one of the main aspects of designing an effective machine learning model for classifying texts. This technique has more relevance when unstructured data is in question. In this paper, a comparison study of various methods used for text classification is presented. The methods are broadly categorized into two major types. One is without feature expansion and the other with Hypernym-Hyponym based feature expansions. Different machine learning algorithms under both the categories are mentioned. The datasets, algorithms, results of evaluation of various algorithms are surveyed and tabulated.