Modified K-Nearest Neighbor Web Based Chatbot as Service and Academic Information School

Abstract

At a time when everything is done on an Online basis starting from office activities, teaching and learning activities especially administrative activities school. Where in the activity, aninformant needs to be can serve academic and non-academic information needs for para parents of students and other parties. Chatbot is one of the means to overcome these needs by presentingfeatures that allows for someone to ask when and where. Therefore, in the conclusion that chatbot can be a public means especially on schools - schools that can implement their uses as one school information sources other than the school's business. This Chatbot made using the Modified K-Nearest Neighbor method or can be briefed MKNN. MKNN is the latest version of the previous method, K-Nearest Neighbor where in the application MKNN method does the process additional after Euclidean Distance calculation, Weight Voting. Premise from the weight voting method itself is the biggestweight calculation, so chatbot will calculate the value of the shortest distance to the database from the chatbot then after completion, the chatbot will calculate the value weight or information from that distance so that the results that can be from this are the shortestdistance to the data class that is being addressed by carrying the weight of information biggest or most. This is used to facilitate the deep chatbot determine the category of a database so that it can provide answers that more certain and accurate.