Phonetic Similarity Analysis of Indonesian Text: Comparing Custom Soundex, Jaro-Winkler, Cosine Similarity, and Euclidean Distance
DOI:
https://doi.org/10.5281/zenodo.24011832Keywords:
phonetic similarity, Indonesian language, Soundex, Jaro-Winkler, grapheme-to-phoneme, fuzzy string matchingAbstract
Indonesian text exhibits rich phonetic variation: regional spelling variants, old-to-new orthography changes such as tj→c and oe→u, and digraphs such as ng, ny, kh, and sy that standard phonetic algorithms designed for English fail to capture. This paper presents a comparative analysis of four phonetic similarity algorithms on Indonesian word pairs: (1) a Custom Soundex adapted to Indonesian phonology with 5-digit codes, digraph-aware encoding, old-spelling normalization, and silent-h stripping; (2) Jaro-Winkler similarity computed on grapheme-to-phoneme (G2P) representations, implemented as phoneme similarity via soft Levenshtein distance with phoneme-class substitution costs; (3) Cosine Similarity over positional phoneme vectors with a length-ratio penalty; and (4) Euclidean Distance over the same positional vectors. The evaluation uses a dataset of 10,000 Indonesian word pairs labeled Mirip (similar) or Beda (different), balanced 5,000/5,000 across phonetically similar and control pairs. Decision thresholds were tuned per method: identical codes for Soundex, 0.80 for Jaro-Winkler+G2P, 0.65 for Cosine Similarity, and a distance of 1.5 for Euclidean. Each algorithm classifies pairs with its tuned decision threshold. Custom Soundex ID achieved the best performance with 99.2% accuracy and an F1-score of 0.992, followed by Cosine Similarity (94.9%, F1 0.948), Jaro-Winkler+G2P (91.9%, F1 0.912), and Euclidean Distance (91.7%, F1 0.910). Confusion matrix analysis shows that phoneme-aware encoding resolves most false positives caused by coincidental prefix overlap and subword absorption. The main contribution is empirical evidence that a lightweight, linguistically informed phonetic code outperforms generic string similarity measures for Indonesian, together with a documented preprocessing pipeline of orthography normalization, G2P conversion, and silent-h stripping that is reusable for Indonesian fuzzy text matching.
References
[2] L. Philips, "The double metaphone search algorithm," C/C++ Users Journal, vol. 18, no. 6, pp. 38-43, Jun. 2000.
[3] V. Gautam, A. Pipal, and M. Arora, "SoundEx algorithm revisited for Indian language," in Proc. Int. Conf. Innovative Computing and Communications (ICICC 2018), Lecture Notes in Networks and Systems, vol. 56, Singapore: Springer, 2019. DOI: 10.1007/978-981-13-2354-6_6
[4] D. Pinto, D. Vilarino, Y. Aleman, H. Gomez, N. Loya, and H. Jimenez-Salazar, "The Soundex phonetic algorithm revisited for SMS text representation," in Text, Speech and Dialogue (TSD 2012), Lecture Notes in Computer Science, vol. 7499, Berlin: Springer, pp. 47-55, 2012. DOI: 10.1007/978-3-642-32790-2_5
[5] H. Lapoliwa, A Generative Approach to the Phonology of Bahasa Indonesia, Pacific Linguistics, Series D, no. 34, Canberra: Australian National University, 1981. DOI: 10.15144/PL-D34
[6] J. Asian, H. E. Williams, and S. M. M. Tahaghoghi, "Stemming Indonesian," in Proc. 28th Australasian Computer Science Conf. (ACSC 2005), Conferences in Research and Practice in Information Technology, vol. 38, Newcastle, Australia, pp. 307-314, 2005.
[7] M. Adriani, J. Asian, B. Nazief, S. M. M. Tahaghoghi, and H. E. Williams, "Stemming Indonesian: A confix-stripping approach," ACM Trans. Asian Language Information Processing, vol. 6, no. 4, pp. 1-33, Dec. 2007. DOI: 10.1145/1316457.1316459
[8] B. Wilie et al., "IndoNLU: Benchmark and resources for evaluating Indonesian natural language understanding," in Proc. 1st Conf. Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th Int. Joint Conf. Natural Language Processing (AACL-IJCNLP 2020), Suzhou, pp. 843-857, 2020. DOI: 10.18653/v1/2020.aacl-main.85
[9] M. A. Jaro, "Advances in record-linkage methodology as applied to matching the 1985 census of Tampa, Florida," J. Amer. Statistical Association, vol. 84, no. 406, pp. 414-420, Jun. 1989. DOI: 10.1080/01621459.1989.10478785
[10] W. E. Winkler, "String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage," in Proc. Section on Survey Research Methods, American Statistical Association, pp. 354-359, 1990.
[11] V. I. Levenshtein, "Binary codes capable of correcting deletions, insertions, and reversals," Soviet Physics Doklady, vol. 10, no. 8, pp. 707-710, 1966.
[12] G. Navarro, "A guided tour to approximate string matching," ACM Computing Surveys, vol. 33, no. 1, pp. 31-88, Mar. 2001. DOI: 10.1145/375360.375365
[13] W. W. Cohen, P. Ravikumar, and S. E. Fienberg, "A comparison of string distance metrics for name-matching tasks," in Proc. IJCAI-03 Workshop on Information Integration on the Web (IIWeb-03), Acapulco, Mexico, pp. 73-78, 2003.
[14] K. Kukich, "Techniques for automatically correcting words in text," ACM Computing Surveys, vol. 24, no. 4, pp. 377-439, Dec. 1992. DOI: 10.1145/146370.146380
[15] I. P. Fellegi and A. B. Sunter, "A theory for record linkage," J. Amer. Statistical Association, vol. 64, no. 328, pp. 1183-1210, Dec. 1969. DOI: 10.1080/01621459.1969.10501049
[16] A. K. Elmagarmid, P. G. Ipeirotis, and V. S. Verykios, "Duplicate record detection: A survey," IEEE Trans. Knowledge and Data Engineering, vol. 19, no. 1, pp. 1-16, Jan. 2007. DOI: 10.1109/TKDE.2007.250581
[17] A. W. Black, K. Lenzo, and V. Pagel, "Issues in building general letter to sound rules," in Proc. 3rd ESCA/COCOSDA Workshop on Speech Synthesis, Jenolan Caves, Australia, pp. 77-80, 1998.
[18] M. Bisani and H. Ney, "Joint-sequence models for grapheme-to-phoneme conversion," Speech Communication, vol. 50, no. 5, pp. 434-451, May 2008. DOI: 10.1016/j.specom.2008.01.002
[19] A. Deri and K. Knight, "Grapheme-to-phoneme models for (almost) any language," in Proc. 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), Berlin, pp. 399-408, 2016. DOI: 10.18653/v1/P16-1038
[20] D. Holmes and M. C. McCabe, "Improving precision and recall for Soundex retrieval," in Proc. Int. Conf. Information Technology: Coding and Computing (ITCC 2002), pp. 22-26, 2002. DOI: 10.1109/ITCC.2002.1000354
[21] J. Zobel and P. Dart, "Finding approximate matches in large lexicons," Software: Practice and Experience, vol. 25, no. 3, pp. 331-345, Mar. 1995. DOI: 10.1002/spe.4380250307
[22] H. Raghavan and J. Allan, "Using Soundex codes for indexing names in ASR documents," in Proc. Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval at HLT-NAACL 2004, Boston, MA, pp. 22-27, 2004.
[23] G. Salton, A. Wong, and C. S. Yang, "A vector space model for automatic indexing," Communications of the ACM, vol. 18, no. 11, pp. 613-620, Nov. 1975. DOI: 10.1145/361219.361220
[24] G. Salton and C. Buckley, "Term-weighting approaches in automatic text retrieval," Information Processing & Management, vol. 24, no. 5, pp. 513-523, 1988. DOI: 10.1016/0306-4573(88)90021-0
[25] G. Kondrak, "N-gram similarity and distance," in String Processing and Information Retrieval (SPIRE 2005), Lecture Notes in Computer Science, vol. 3772, Berlin: Springer, pp. 115-126, 2005. DOI: 10.1007/11575832_13
[26] M. Sokolova and G. Lapalme, "A systematic analysis of performance measures for classification tasks," Information Processing & Management, vol. 45, no. 4, pp. 427-437, Jul. 2009. DOI: 10.1016/j.ipm.2009.03.002
[27] T. Fawcett, "An introduction to ROC analysis," Pattern Recognition Letters, vol. 27, no. 8, pp. 861-874, Jun. 2006. DOI: 10.1016/j.patrec.2005.10.010
[28] P. Christen, Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection, Data-Centric Systems and Applications, Berlin: Springer, 2012. DOI: 10.1007/978-3-642-31164-2
[29] A. Hapsari and Suyahman, "Comparative Analysis of Trademark Class Identification Using IndoBERT and Multilingual BERT," J. Artificial Intelligence and Legal Technology, vol. 1, no. 1, pp. 1-8, 2025.
[30] M. A. Pratama and Suyahman, "Semantic Analysis of Trademark Names Using Large Language Models," J. Artificial Intelligence and Legal Technology, vol. 1, no. 1, pp. 15-26, 2025.
