An Improved Chinese String Comparator for Bloom Filter Based Privacy-Preserving Record Linkage
Open Access
Abstract
With the development of information technology, it has become a popular topic to share data from multiple sources without privacy disclosure problems. Privacy-preserving record linkage (PPRL) can link the data that truly matches and does not disclose personal information. In the existing studies, the techniques of PPRL have mostly been studied based on the alphabetic language, which is much different from the Chinese language environment. In this paper, Chinese characters (identification fields in record pairs) are encoded into strings composed of letters and numbers by using the SoundShape code according to their shapes and pronunciations. Then, the SoundShape codes are encrypted by Bloom filter, and the similarity of encrypted fields is calculated by Dice similarity. In this method, the false positive rate of Bloom filter and different proportions of sound code and shape code are considered. Finally, we performed the above methods on the synthetic datasets, and compared the precision, recall, F1-score and computational time with different values of false positive rate and proportion. The results showed that our method for PPRL in Chinese language environment improved the quality of the classification results and outperformed others with a relatively low additional cost of computation.Keywords
Funding Information
- National Natural Science Foundation of China (81701794)
- National Innovation and Entrepreneurship Training Program of under Graduate (202010504076)
This publication has 21 references indexed in Scilit:
- Secure pseudonymisation for privacy-preserving probabilistic record linkageJournal of Information Security and Applications, 2017
- Privacy-Preserving Record Linkage for Big Data: Current Approaches and Research Challenges2017
- Privacy-preserving record linkage on large real world datasetsJournal of Biomedical Informatics, 2014
- Implementation of an extended Fellegi-Sunter probabilistic record linkage method using the Jaro-Winkler string comparator2014
- Composite Bloom Filters for Secure Record LinkageIEEE Transactions on Knowledge and Data Engineering, 2013
- Efficient privacy-aware record integration2013
- Privacy-preserving record linkage using Bloom filtersBMC Medical Informatics and Decision Making, 2009
- Compressed Bloom filtersIEEE/ACM Transactions on Networking, 2002
- Better Filtering with Gapped q-GramsLecture Notes in Computer Science, 2001
- Record Linkage Strategies, Outpatient Procedures, and Administrative DataMedical Care, 1996