Phonetic coding methods for Malay names retrieval

Searching for person names has been very popular among users of information systems and search engines. Thus, the effectiveness, accuracy and appropriateness of search results are strongly emphasized. Information retrieval (IR) methods provide high impact in influencing the searching results. Efforts in improving the IR methods have been made due to the fact that names are not unique and have varieties of spelling. This will caused errors during the process of getting accurate names. Searching based on phonetic is said to be a suitable method to solve the aforementioned problem because names have limited spelling standards. Phonetic method is used to recognize and retrieve words that have the same pronunciation. The main aim of this paper is to test the effectiveness of phonetic coding method on Malay name retrieval using Soundex and modified-Asoundex (Asoundex is an Arabic Soundex). The experimental approach used to perform this research consists of two stages; program development and testing Malay name data sets. The development of programs referred to the existing algorithms to generate name code. Code generated from program will be compared with data contained in the test data. The effectiveness of the result is determined by comparing the output with the result obtained from both phonetic approaches. Evaluation is based on the precision and recall measures. The contribution of the research is to provide comparative accuracy of Malay name retrieval using Soundex and modified-Asoundex coding method. Result show that an average of 38.38% improvement of the precision measure has been achieved.