A holistic comparison study between Chinese and European Cosmetic Regulations through LDA and text mining techniques
534
Presented by: Esther Lai-Fong Ip
Introduction
Since January 01st, 2021, the new Cosmetics Supervision and Administration Regulation (CSAR), released by the China State Council, has come into force and replaced the previous Cosmetics Hygiene Supervision Regulations. CSAR covers the quality and safety of cosmetics, through enhancing the supervision and responsibility. The key changes include new cosmetic definitions & classifications, “new” ingredient registration, addition of efficacy claim supports, responsible person for industry and requirements on product safety assessment. Imported cosmetics also require the submission of certifications relating to manufacturing quality control and supporting documents where the products have been launched in the market. For products specially produced for China market where without these kinds of supporting documents, the applicant must submit related research and test data for Chinese consumers. The newly launched CSAR brings a big impact to both the China and international cosmetics operators.
The framework of CSAR has some similarities with the EU Cosmetics Regulation. Regulation (EC) No 1223/2009 is the main regulatory framework for finished cosmetic products to be placed onto the EU market. It replaces Directive 76/768/EC which was adopted in 1976. The latest EU cosmetic regulation strengthens the safety of cosmetic products, introduction of the responsible person, centralization of the product notification, introduction of reporting of serious undesirable effects (SUE) and new rules for the use of nanomaterials in cosmetic products.
The purpose of this study is to provide a comparison study between the CSAR and European (EU) cosmetics Regulation (EC) No 1223/2009 which entered into force in July 2013.
Methods
The Latent Dirichlet Allocation (LDA) is a generative statistical model that allows sets of observations to be explained by unobserved groups that explain why some parts of the data are similar. One application of LDA is to discover topics in a collection of documents, and then automatically classify any individual document within the collection in terms of how "relevant" it is to each of the discovered topics.
In this study, LDA is applied onto both CSAR and Europe Cosmetic Regulation to find out the major topics and key words of two regulations. These major topics and key words can represent the key focus and concern of government and other stakeholders. They are also the summaries of regulatory background and intent.
Text mining is an artificial intelligence (AI) technology that uses natural language processing (NLP) to transform the free (unstructured) text in documents and databases into normalized, structured data suitable for analysis or to drive machine learning (ML) algorithms.
Text mining technique is applied onto both CSAR and Europe Cosmetic Regulation, for transforming to structured data-sets. The structured data-set is used for descriptive and prescriptive analytics for details and focus about regulatory implementation.
Expert interviews are also conducted. Results by LDA and text mining are compared with the experts’ opinions.
Results
The study finds the similarities and differences of these two regulations.
Major topics and key words in these two regulations would be obtained by LDA in this study.
Results about details and focus of regulatory implementation under the two frameworks would also be attained through text mining techniques, in the aspects of descriptive and prescriptive analytics.
The results are compared with the experts’ opinions as verifying.
Discussion and Conclusion
This study finds the key topics, similarities and potential gaps between two regulations. It can serve as a basis for cosmetic operators who understands EU cosmetic regulation to link to CSAR. Comparison of the CSAR and the European Cosmetic Regulation results in the conclusions that there are similarities in certain areas and mutual understanding. It is clear that the China cosmetic regulation is becoming more and more aligned with international practices. This study can be seen as phase I of comparison study. Phase II study about in-depth analysis is necessary to formulate the explicit practical guidelines for Practitioners in the industry to follow, to comply the regulatory requirements.
Since January 01st, 2021, the new Cosmetics Supervision and Administration Regulation (CSAR), released by the China State Council, has come into force and replaced the previous Cosmetics Hygiene Supervision Regulations. CSAR covers the quality and safety of cosmetics, through enhancing the supervision and responsibility. The key changes include new cosmetic definitions & classifications, “new” ingredient registration, addition of efficacy claim supports, responsible person for industry and requirements on product safety assessment. Imported cosmetics also require the submission of certifications relating to manufacturing quality control and supporting documents where the products have been launched in the market. For products specially produced for China market where without these kinds of supporting documents, the applicant must submit related research and test data for Chinese consumers. The newly launched CSAR brings a big impact to both the China and international cosmetics operators.
The framework of CSAR has some similarities with the EU Cosmetics Regulation. Regulation (EC) No 1223/2009 is the main regulatory framework for finished cosmetic products to be placed onto the EU market. It replaces Directive 76/768/EC which was adopted in 1976. The latest EU cosmetic regulation strengthens the safety of cosmetic products, introduction of the responsible person, centralization of the product notification, introduction of reporting of serious undesirable effects (SUE) and new rules for the use of nanomaterials in cosmetic products.
The purpose of this study is to provide a comparison study between the CSAR and European (EU) cosmetics Regulation (EC) No 1223/2009 which entered into force in July 2013.
Methods
The Latent Dirichlet Allocation (LDA) is a generative statistical model that allows sets of observations to be explained by unobserved groups that explain why some parts of the data are similar. One application of LDA is to discover topics in a collection of documents, and then automatically classify any individual document within the collection in terms of how "relevant" it is to each of the discovered topics.
In this study, LDA is applied onto both CSAR and Europe Cosmetic Regulation to find out the major topics and key words of two regulations. These major topics and key words can represent the key focus and concern of government and other stakeholders. They are also the summaries of regulatory background and intent.
Text mining is an artificial intelligence (AI) technology that uses natural language processing (NLP) to transform the free (unstructured) text in documents and databases into normalized, structured data suitable for analysis or to drive machine learning (ML) algorithms.
Text mining technique is applied onto both CSAR and Europe Cosmetic Regulation, for transforming to structured data-sets. The structured data-set is used for descriptive and prescriptive analytics for details and focus about regulatory implementation.
Expert interviews are also conducted. Results by LDA and text mining are compared with the experts’ opinions.
Results
The study finds the similarities and differences of these two regulations.
Major topics and key words in these two regulations would be obtained by LDA in this study.
Results about details and focus of regulatory implementation under the two frameworks would also be attained through text mining techniques, in the aspects of descriptive and prescriptive analytics.
The results are compared with the experts’ opinions as verifying.
Discussion and Conclusion
This study finds the key topics, similarities and potential gaps between two regulations. It can serve as a basis for cosmetic operators who understands EU cosmetic regulation to link to CSAR. Comparison of the CSAR and the European Cosmetic Regulation results in the conclusions that there are similarities in certain areas and mutual understanding. It is clear that the China cosmetic regulation is becoming more and more aligned with international practices. This study can be seen as phase I of comparison study. Phase II study about in-depth analysis is necessary to formulate the explicit practical guidelines for Practitioners in the industry to follow, to comply the regulatory requirements.