Abstract
Soundex has been proposed as an alternative for Privacy-Preserving Record Linkage featuring significant performance in terms of result quality and efficiency, without, however, the corresponding attention to evaluate its performance with respect to fairness. In this paper, we focus on race and gender biases and examine the behavior of Soundex using a real world dataset and Apache Spark for processing. We compare these results with two other well known phonetic algorithms, namely NYSIIS and Metaphone. Our evaluation indicates that no biases are induced with respect to gender. On the other hand, regarding race, biases have been observed for all examined algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Christen, P.: Data Matching - Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Springer (2012). ISBN: 978-3-642-31163-5
Christen, P., Ranbaduge, T., Schnell, R.: Linking Sensitive Data - Methods and Techniques for Practical Privacy-Preserving Information Sharing. Springer (2020)
Efthymiou, V., Stefanidis, K., Pitoura, E., Christophides, V.: Fairer: entity resolution with fairness constraints. In: CIKM, pp. 3004–3008. ACM (2021)
Gkoulalas-Divanis, A., Vatsalan, D., Karapiperis, D., Kantarcioglu, M.: Modern privacy-preserving record linkage techniques: an overview. IEEE Trans. Inf. Forensics Secur. 16, 4966–4987 (2021)
Karakasidis, A., Koloniari, G.: Efficient privacy preserving record linkage at scale using Apache Spark. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 402–407. IEEE (2022)
Karakasidis, A., Koloniari, G.: More sparking soundex-based privacy-preserving record linkage. In: Foschini, L., Kontogiannis, S. (eds.) International Symposium on Algorithmic Aspects of Cloud Computing, pp. 73–93. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-33437-5_5
Karakasidis, A., Pitoura, E.: Identifying bias in name matching tasks. In: EDBT, pp. 626–629 (2019)
Makri, C., Karakasidis, A., Pitoura, E.: Towards a more accurate and fair SVM-based record linkage. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 4691–4699. IEEE (2022)
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. ACM Comput. Surv. (CSUR) 54(6), 1–35 (2021)
Mishra, S., He, S., Belli, L.: Assessing demographic bias in named entity recognition. CoRR abs/2008.03415 (2020)
Odell, M., Russell, R.C.: The soundex coding system. US Patents 1261167 (1918)
Pessach, D., Shmueli, E.: A review on fairness in machine learning. ACM Comput. Surv. (CSUR) 55(3), 1–44 (2022)
Philips, L.: Hanging on the metaphone. Comput. Lang. 7(12), December 1990
Pitoura, E.: Social-minded measures of data quality: fairness, diversity, and lack of bias. J. Data Inf. Quality (JDIQ) 12(3), 1–8 (2020)
Taft, R.: Name search techniques. Tech. rep, New York State Identification and Intelligence System, Albany, N.Y. (1970)
Vatsalan, D., Yu, J., Henecka, W., Thorne, B.: Fairness-aware privacy-preserving record linkage. In: Garcia-Alfaro, J., Navarro-Arribas, G., Herrera-Joancomarti, J. (eds.) DPM/CBT -2020. LNCS, vol. 12484, pp. 3–18. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66172-4_1
Wu, N., Vatsalan, D., Verma, S., Kâafar, M.A.: Fairness and cost constrained privacy-aware record linkage. IEEE Trans. Inf. Forensics Secur. 17, 2644–2656 (2022)
Zaharia, M., et al.: Apache Spark: a unified engine for big data processing. Commun. ACM 59(11), 56–65 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Karakasidis, A., Koloniari, G. (2023). Exploring Biases for Privacy-Preserving Phonetic Matching. In: Abelló, A., et al. New Trends in Database and Information Systems. ADBIS 2023. Communications in Computer and Information Science, vol 1850. Springer, Cham. https://doi.org/10.1007/978-3-031-42941-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-42941-5_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42940-8
Online ISBN: 978-3-031-42941-5
eBook Packages: Computer ScienceComputer Science (R0)