<![CDATA[The National Police of the Republic of Indonesia is one of the law enforcers in the Unitary State of the Republic of Indonesia. One of the tasks of the Indonesian Police is to provide services to the community. Accusation of crime is one form of service to the community offered by the Police. Crime can happen to anyone no matter an employee, a student or others. The stage after the report of a crime is received by the police is the issuance of investigation. However, within one month the police had difficulty classifying every police report that have been accepted especially Polres Kota Malang. Therefore a system for helping the police to classified a accusation of crime into three cases are persecution, stealing, and fraud is needed. Process in this study is by doing a pre-processing text which the next stage is counting the weight of tf, df, and idf and continue to classification. In this study classification do by using BM25 and Improved K-Nearest Neighbor Methods (IKNN). The results of the k-fold cross validation test, the highest average value of precision=0,953373, recall=0,931382, f-measure=0,938122 and accuracy=0,956795 at the value of k = 15.]]>
Copyrights © 2019
