This article proposes the modified KNN (K Nearest Neighbor) algorithm which receives a string vector as its input data and is applied to the keyword extraction. The results from applying the string vector based algorithms to the text categorizations were successful in previous works and the keyword extraction is able to be mapped into the binary classification where each word is classified into keyword or non-keyword. In the proposed system, a text which is given as the input is indexed into a list of words, each word is classified by the proposed KNN version, and the words which are classified into keyword are extracted ad the output. The proposed KNN version is empirically validated as the better approach in deciding whether each word is a keyword or non-keyword in news articles and opinions. We need to define and characterize mathematically more operations on string vectors for modifying more advanced machine learning algorithms.