DETEKSI KATA TAK BAKU DAN KESALAHAN PENULISAN KATA PADA TUGAS AKHIR MAHASISWA MENGGUNAKAN METODE DICTIONARY LOOKUP

Abstract

Dictionary lookup is a simple searching method that aimed to find a word in the dictionary. The technique is effectively implemented to find the incorrect spelling based on the lexical resource. This research will create a system to detect non-standard and misspell words by looking into Standard Indonesian Language Dictionary (KBBI) and Kateglo Dictionary. In addition, the lookup process of the system is optimized by utilizing an index in the database. To validate the system, the front-end interface is created by displaying the options for end-user to upload their documents. The system will be evaluated by using 40 documents of the students' final project. The testing result shows that the average document processing speed is 187 words per second. The average of incorrect words in each document is 2.76%, with a precision value is 28.71%. The low precision is caused by the higher value of False Positive, which was determined by non-existence words in the dictionary. However, the system has shown good performance by obtaining higher True Negative values from each document which implies the accuracy is also high.