This section is concerned with modifying the AHC (Agglomerative Hierarchical Clustering) algorithm into the version which considers the similarities among features as well as feature values, and it consists of the three sections. In Section 3.1, we describe the process of encoding words into numerical vectors. In Section 3.2, we do formally the proposed scheme of computing the similarity between two numerical vectors. In Section ??, we mention the proposed version of AHC algorithm which considers the similarity among features as the approach to word clustering. Therefore, this article is intended to describe in detail the modified version of KNN algorithm and its application to the word clustering.