Valid or Just Viral? Post-Purchase Consumer Sentiment and Regulatory Discourse on Imported Vitamins on Shopee

Rusda; Syamsu Alam; Ayu Latifah Alfisyahrin; Ainul Fatha Isman

doi:10.61255/jeemba.v4i5.1729

Authors

Rusda Universitas Hasanuddin, Makassar, Indonesia
Syamsu Alam Universitas Negeri Makassar, Makassar, Indonesia
Ayu Latifah Alfisyahrin Universitas Hasanuddin, Makassar, Indonesia
Ainul Fatha Isman Universitas Hasanuddin, Makassar, Indonesia

DOI:

https://doi.org/10.61255/jeemba.v4i5.1729

Keywords:

BPOM, E-commerce, Halal certification, Machine learning, Post-purchase review, Sentiment analysis

Abstract

Purpose – This study examines sentiment and recurring topics in post-purchase reviews of imported vitamin products whose Shopee listings did not clearly display halal certification or Badan Pengawas Obat dan Makanan (BPOM; Indonesian Food and Drug Authority) registration information. It assesses whether halal and BPOM appear explicitly in consumer-generated reviews.

Design/methodology/approach – A quantitative descriptive design combined manual reference labelling, supervised sentiment classification, and descriptive lexical analysis. One researcher labelled 250 verified-buyer reviews from seven products and coded recurring keywords. Raw text was divided through a stratified 80:20 train-test split before term frequency–inverse document frequency (TF-IDF) with unigram and bigram features was fitted on the training text and applied to the held-out text. Multinomial Naive Bayes, Logistic Regression, Linear Support Vector Classifier (LinearSVC), and Random Forest were evaluated using overall, macro, weighted, class-specific, and confusion-matrix measures.

Findings – Neutral labels predominated (58.0%), followed by positive (31.6%) and negative (10.4%) labels. Random Forest achieved the strongest performance within the experiment (accuracy = 0.80; macro F1 = 0.65), followed by LinearSVC (accuracy = 0.78; macro F1 = 0.63), although both detected only one of five negative test cases. Recurring themes concerned authenticity, packaging, delivery, expiration dates, and product condition. “halal” did not occur, and one BPOM-related expression was identified.

Originality/value – The study complements intention-based halal consumer research by analysing naturally occurring post-purchase discourse while distinguishing review content from pre-purchase decision-making and official regulatory status. It also separates classifier performance from the substantive label distribution in a small, imbalanced dataset.

Abstract views: 16 ,

PDF downloads: 3

Downloads

Download data is not yet available.

References

Abighail, B. M. D., Fachrifansyah, Firmanda, M. R., Anggreainy, M. S., Harvianto, & Gintoro. (2023). Sentiment analysis e-commerce review. Procedia Computer Science, 227, 1039–1045. https://doi.org/10.1016/j.procs.2023.10.613

Ajzen, I. (1991). The theory of planned behavior. Organizational Behavior and Human Decision Processes, 50(2), 179–211. https://doi.org/10.1016/0749-5978(91)90020-T

Ali, A., Xiaoling, G., Sherwani, M., & Ali, A. (2018). Antecedents of consumers’ Halal brand purchase intention: An integrated approach. Management Decision, 56(4), 715–735. https://doi.org/10.1108/MD-11-2016-0785

Badan Pengawas Obat dan Makanan Republik Indonesia. (2023). Cek produk: Database registrasi produk. Retrieved from https://cekbpom.pom.go.id

Badan Pengawas Obat dan Makanan Republik Indonesia. (2025, April 30). BPOM ungkap 39.642 tautan ilegal produk obat dan makanan di media daring. Retrieved from https://siber.pom.go.id/berita/bpom-ungkap-39-642-tautan-ilegal-produk-obat-dan-makanan-di-media-daring

Badan Penyelenggara Jaminan Produk Halal. (2025). Produk bersertifikat halal tembus 9,6 juta, BPJPH terus intensifkan kolaborasi dalam & luar negeri. Retrieved from https://bpjph.halal.go.id/read/produk-bersertifikat-halal-tembus-9-6-juta-bpjph-terus-intensifkan-kolaborasi-dalam-and-luar-negeri

Bhutto, M. Y., Rūtelionė, A., & Vienažindienė, M. (2024). Investigating EWOM and halal product knowledge on Gen Z’s halal cosmetics purchase intentions in Pakistan. Journal of Islamic Marketing, 15(11), 3266–3281. https://doi.org/10.1108/JIMA-09-2023-0292

Chebolu, S. U. S., Dernoncourt, F., Lipka, N., & Solorio, T. (2023). A review of datasets for aspect-based sentiment analysis. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (pp. 611–628). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.ijcnlp-main.41

Chen, Y., & Xie, J. (2008). Online consumer review: Word-of-mouth as a new element of marketing communication mix. Management Science, 54(3), 477–491. https://doi.org/10.1287/mnsc.1070.0810

Crawford, C., Avula, B., Lindsey, A. T., Walter, A., Katragunta, K., Khan, I. A., & Deuster, P. A. (2022). Analysis of select dietary supplement products marketed to support or boost the immune system. JAMA Network Open, 5(8), e2226040. https://doi.org/10.1001/jamanetworkopen.2022.26040

Filieri, R. (2015). What makes online reviews helpful? A diagnosticity-adoption framework to explain informational and normative influences in e-WOM. Journal of Business Research, 68(6), 1261–1270. https://doi.org/10.1016/j.jbusres.2014.11.006

Floyd, K., Freling, R., Alhoqail, S., Cho, H. Y., & Freling, T. (2014). How online product reviews affect retail sales: A meta-analysis. Journal of Retailing, 90(2), 217–232. https://doi.org/10.1016/j.jretai.2014.04.004

Golovan, T. V. (2024). The on-line turnover of biologically active additives. Part 2. Customs control for the turnover of imported dietary supplements on marketplaces as a measure to protect the life and health of citizens. Problemy Sotsial’noi Gigieny, Zdravookhraneniia i Istorii Meditsiny, 32(3), 363–369. https://doi.org/10.32687/0869-866X-2024-32-3-363-369

Handoyo, S. (2024). Purchasing in the digital age: A meta-analytical perspective on trust, risk, security, and e-WOM in e-commerce. Heliyon, 10(8), e29714. https://doi.org/10.1016/j.heliyon.2024.e29714

Hua, Y. C., Denny, P., Wicker, J., & Taskova, K. (2024). A systematic review of aspect-based sentiment analysis: Domains, methods, and trends. Artificial Intelligence Review, 57, Article 296. https://doi.org/10.1007/s10462-024-10906-z

Izza, N. N., & Akbar, N. (2023). Uncovering halal label food purchase intention behavior in Indonesia: A Twitter analytics and SEM-based investigation. Jurnal Ekonomi Syariah Teori Terapan, 10(6), 551–570. https://doi.org/10.20473/vol10iss20236pp551-570

Khan, Z., Khan, A., Nazish, M., & Arwab, M. (2026). A fusion of TAM and TPB with halal product knowledge and religiosity to understand online purchase intentions of halal cosmetics among Muslims Gen Z. Journal of Islamic Marketing, 17(4), 1415–1437. https://doi.org/10.1108/JIMA-10-2024-0456

Liu, B. (2020). Sentiment analysis: Mining opinions, sentiments, and emotions (2nd ed.). Cambridge University Press.

Mao, Y., Liu, Q., & Zhang, Y. (2024). Sentiment analysis methods, applications, and challenges: A systematic literature review. Journal of King Saud University – Computer and Information Sciences, 36, Article 102048. https://doi.org/10.1016/j.jksuci.2024.102048

Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093–1113. https://doi.org/10.1016/j.asej.2014.04.011

Mou, J., & Benyoucef, M. (2021). Consumer behavior in social commerce: Results from a meta-analysis. Technological Forecasting and Social Change, 167, Article 120734. https://doi.org/10.1016/j.techfore.2021.120734

Mudambi, S. M., & Schuff, D. (2010). What makes a helpful online review? A study of customer reviews on Amazon.com. MIS Quarterly, 34(1), 185–200. https://doi.org/10.2307/20721420

Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (pp. 79–86). Association for Computational Linguistics. https://doi.org/10.3115/1118693.1118704

Rathmann, A.-M., & Seifert, R. (2024). Vitamin A-containing dietary supplements from German and US online pharmacies: Market and risk assessment. Naunyn-Schmiedeberg’s Archives of Pharmacology, 397(9), 6803–6820. https://doi.org/10.1007/s00210-024-03050-6

Sharma, N. A., Shawkat Ali, A. B. M., & Kabir, M. A. (2025). A review of sentiment analysis: Tasks, applications, and deep learning techniques. International Journal of Data Science and Analytics, 19(3), 351–388. https://doi.org/10.1007/s41060-024-00594-x

Shopee. (2025). Seller center feature for entering halal certification numbers and BPOM registration numbers. Retrieved from https://seller.shopee.co.id

Susanty, A., Puspitasari, N. B., Jie, F., Akhsan, F. A., & Jati, S. (2025). Consumer acceptance of halal food traceability systems: A novel integrated approach using modified UTAUT and DeLone & McLean models to promote sustainable food supply chain practices. Cleaner Logistics and Supply Chain, 15, Article 100226. https://doi.org/10.1016/j.clscn.2025.100226

Tedjakusuma, A. P., Au Yong, H. N., Andajani, E., & Mohamad, Z. Z. (2023). Intention to purchase halal health supplement online: Lessons learned from the health crisis. Heliyon, 9(9), e19840. https://doi.org/10.1016/j.heliyon.2023.e19840

White, C. M. (2022). Continued risk of dietary supplements adulterated with approved and unapproved drugs: Assessment of the US Food and Drug Administration’s Tainted Supplements Database 2007 through 2021. The Journal of Clinical Pharmacology, 62(8), 928–934. https://doi.org/10.1002/jcph.2046

Wilson, J. A. J., & Liu, J. (2010). Shaping the Halal into a brand? Journal of Islamic Marketing, 1(2), 107–123. https://doi.org/10.1108/17590831011055851