AdSafe Analyzer: A Rule-Based Compliance Checker for Thai Healthcare Advertising

Phichitphon Chotikunnan; Wanida Khotakham; Pariwat Imura; Rawiphon Chotikunnan; Pichit Boonkrong; Nuntachai Thongpance; Paweena Suksuwan

doi:10.48084/etasr.16267

Authors

Phichitphon Chotikunnan College of Biomedical Engineering, Rangsit University, Pathum Thani, Thailand
Wanida Khotakham College of Biomedical Engineering, Rangsit University, Pathum Thani, Thailand
Pariwat Imura College of Biomedical Engineering, Rangsit University, Pathum Thani, Thailand
Rawiphon Chotikunnan College of Biomedical Engineering, Rangsit University, Pathum Thani, Thailand
Pichit Boonkrong College of Biomedical Engineering, Rangsit University, Pathum Thani, Thailand
Nuntachai Thongpance College of Biomedical Engineering, Rangsit University, Pathum Thani, Thailand
Paweena Suksuwan Graduate School, Rangsit University, Pathum Thani, Thailand

Volume: 16 | Issue: 2 | Pages: 34211-34218 | April 2026 | https://doi.org/10.48084/etasr.16267

Received: 14 November 2025 | Revised: 13 December 2025 and 9 January 2026 | Accepted: 13 January 2026 | Online: 4 April 2026
Corresponding author: Wanida Khotakham

Abstract

Healthcare advertising is subject to strict regulatory and ethical standards to prevent misleading claims, which also applies in the digital environment. This study presents AdSafe Analyzer (ASA), which is a web-based, rule-driven platform designed to support regulatory compliance in healthcare and cosmetic advertising in Thailand. ASA functions as a pre-publication screening tool, evaluating advertising content against a standardized set of keywords derived from regulatory guidelines, categorizing expressions as legal, conditionally permitted, or prohibited. The system utilizes a phrase-level reverse-search pattern-matching technique with text normalization, enabling real-time identification of restricted expressions without relying on intricate language models. The system was evaluated using curated datasets, comprising restricted phrases, sentence-level instances, and a negative control corpus of conforming advertisements, demonstrating perfect recall, precision, and F1-score values of 1.00, with no False Positives (FPs) observed under the tested conditions. Therefore, by providing an efficient and transparent pre-publication compliance check, ASA mitigates regulatory risk and promotes responsible communication in healthcare advertising. A live prototype of the system is available at http://researchbme.rsu.ac.th/ASA_V1/index.html.

Keywords:

advertisement analysis, web application, keyword filtering, text screening system, prohibited keywords, marketing safety, advertising regulation

Downloads

Download data is not yet available.

References

Department of Health Service Support, Ministry of Public Health, Thailand, "Guidelines for hospital and clinic advertising," [Online]. Available: https://hss.moph.go.th/webs/law/fileupload_doc/2023-03-22-7-21-3471541.pdf.

A. Alqahtani, H. Alhakami, T. Alsubait, and A. Baz, "A Survey of Text Matching Techniques," Engineering, Technology & Applied Science Research, vol. 11, no. 1, pp. 6656–6661, Feb. 2021. DOI: https://doi.org/10.48084/etasr.3968

A. Gupta and R. Katarya, "Social media based surveillance systems for healthcare using machine learning: A systematic review," Journal of Biomedical Informatics, vol. 108, Aug. 2020, Art. no. 103500. DOI: https://doi.org/10.1016/j.jbi.2020.103500

R. J. Chen et al., "Algorithmic fairness in artificial intelligence for medicine and healthcare," Nature Biomedical Engineering, vol. 7, no. 6, pp. 719–742, June 2023. DOI: https://doi.org/10.1038/s41551-023-01056-8

R. C. Chan and P. L. A. Ching, "Pharmacy practice in Thailand," American Journal of Health-System Pharmacy, vol. 62, no. 13, pp. 1408–1411, July 2005. DOI: https://doi.org/10.2146/ajhp040393

K. D. Jain and S. B. Patil, "Overview of Medical Device Regulations in Singapore and Thailand," Biomedical Materials & Devices, vol. 3, no. 1, pp. 259–276, Mar. 2025. DOI: https://doi.org/10.1007/s44174-024-00188-y

B. Tenni, J. Lexchin, C. Akaleephan, C. Kittitrakul, B. Townsend, and D. Gleeson, "Factors influencing the prioritisation of access to medicines in trade‐related intellectual property policymaking in Thailand," The Journal of World Intellectual Property, vol. 27, no. 3, pp. 532–562, Nov. 2024. DOI: https://doi.org/10.1111/jwip.12316

V. Kalaiselvan, A. G., and A. Sharma, "Medical device’s regulation in South-East Asian countries: Current status and gap areas," Asian Journal of Pharmaceutical Research, pp. 173–179, Aug. 2021. DOI: https://doi.org/10.52711/2231-5691.2021.00032

R. Mühlhoff and T. Willem, "Social media advertising for clinical studies: Ethical and data protection implications of online targeting," Big Data & Society, vol. 10, no. 1, Jan. 2023. DOI: https://doi.org/10.1177/20539517231156127

A. Y. L. Chan et al., "Gabapentinoid consumption in 65 countries and regions from 2008 to 2018: a longitudinal trend study," Nature Communications, vol. 14, no. 1, Aug. 2023, Art. no. 5005. DOI: https://doi.org/10.1038/s41467-023-40637-8

N. A. Said, "Data Mining for Managing and Using Online Information on Facebook," Journal of Advances in Information Technology, vol. 14, no. 4, pp. 769–776, 2023. DOI: https://doi.org/10.12720/jait.14.4.769-776

Q. M. Alzubi, S. N. Makhadmeh, and Y. Sanjalawe, "Optimizing Intrusion Detection: Advanced Feature Selection and Machine Learning Techniques Using the CSE-CIC-IDS2018 Dataset," Journal of Advances in Information Technology, vol. 16, no. 3, pp. 283–302, 2025. DOI: https://doi.org/10.12720/jait.16.3.283-302

N. A. Said, "Advancing News Text Classification: A Comparative Analysis of Deep Neural Network Models," Journal of Advances in Information Technology, vol. 16, no. 5, pp. 686–695, 2025. DOI: https://doi.org/10.12720/jait.16.5.686-695

N. Boucher and R. Anderson, "Trojan source: invisible vulnerabilities," in Proceedings of the 32nd USENIX conference on security symposium, Anaheim, CA, USA, 2023.

K. Paripremkul and O. Sornil, "Segmenting Words in Thai Language Using Minimum Text Units and Conditional Random Field," Journal of Advances in Information Technology, vol. 12, no. 2, pp. 135–141, 2021. DOI: https://doi.org/10.12720/jait.12.2.135-141

T. Soisoonthorn, H. Unger, and M. Maliyaem, "Thai Word Segmentation with a Brain‐Inspired Sparse Distributed Representations Learning Memory," Computational Intelligence and Neuroscience, vol. 2023, no. 1, Jan. 2023, Art. no. 8592214. DOI: https://doi.org/10.1155/2023/8592214

T. Chay-intr, H. Kamigaito, and M. Okumura, "Character-Based Thai Word Segmentation with Multiple Attentions," Journal of Natural Language Processing, vol. 30, no. 2, pp. 372–400, 2023. DOI: https://doi.org/10.5715/jnlp.30.372

S. Jintawatsakoon and E. Poonsawat, "Gender Classification of Social Network Text Using Natural Language Processing and Machine Learning Approaches," in 2023 20th International Joint Conference on Computer Science and Software Engineering (JCSSE), Phitsanulok, Thailand, June 2023, pp. 415–420. DOI: https://doi.org/10.1109/JCSSE58229.2023.10201986

N. Khamphakdee and P. Seresangtakul, "An Efficient Deep Learning for Thai Sentiment Analysis," Data, vol. 8, no. 5, May 2023, Art. no. 90. DOI: https://doi.org/10.3390/data8050090

R. Arreerard, S. Mander, and S. Piao, "Survey on Thai NLP language resources and tools," in Proceedings of the thirteenth language resources and evaluation conference, Marseille, France, June 2022, pp. 6495–6505.

V. Vichianchai, "Thai Word Segmentation using a Replacing the English Alphabet Approach to Enhance Thai Text Sentiment Analysis," Journal of Applied Informatics and Technology, vol. 6, 2024, Art. no. 158178.