Sentiment Analysis and Topic Modeling Study: The Comparison of Cosmetics Product Online Reviews
Keywords:Comparation, Online Customer Review, Sentiment Analysis, Topic Modeling
In the competition, companies must orient themselves to serve clients, engage with rivals, and launch products to build a dynamic and competitive corporate environment. The need to meet basic requirements such as clothes, food, and boards, which were formerly straightforward, became increasingly complicated. This can be proven by the development of the cosmetic industry which is marked by the variety of cosmetics on the market. There is currently a need for brand comparison in the business competition since it can make it simpler to understand the strengths and weaknesses of rival companies and serve as a model for enhancing the quality of well-liked items and marketplaces. Indonesia is a very attractive cosmetic market where cosmetic sales data are consistently rising from year to year. Due to the rapid advancement of information technology, buyers now write reviews on social media in addition to conducting online shopping. These online reviews can be helpful for comprehending the shopping process and discussing a product, and affect the customer's plans to make additional purchases in the future. This study compared customer perception of three cosmetics products: powder foundation products from local brands that are Make Over Powerstay Matte Powder Foundation, ESQA Flawless Powder Foundation, and Luxcrime Blur&Cover Two Way Cake, using an online review that was extracted and scraped from a website through the Octoparse Windows program version 8.5.0. This study uses sentiment analysis and topic modeling to compare online reviews of customer perceptions of the three cosmetic products. The result shows the sentiment comparison among three cosmetics brands. The first position is the ESQA brand, followed by the Luxcrime brand, and the last rank is Make Over, with the smallest positive sentiment. The positive brand topics of the three products, in general, are about formulas that are long-lasting and have good coverage, while the negative brand topics, in general, are about formulas that must be reused and transferred when wearing masks.
PPAK Indonesia, “PPA Kosmetika,” PPAK Indonesia, 2021. https://ppakosmetika.com/.
Jakpat.net, “blog.jakpat.net,” 2021. https://blog.jakpat.net/2021-beauty-trends-jakpat-survey-report/ (accessed Sep. 06, 2022).
Compas.co.id, “Data Penjualan 10 Brand Bedak Terlaris Shopee dan Tokopedia: Lokal Bersaing!,” 2021. https://compas.co.id/article/bedak-terlaris/.
Review.soco.id, “review.soco.id,” 2022. https://review.soco.id/product/pressed-powder/81390-flawless-powder-foundation (accessed Feb. 21, 2022).
I. Ahmad, T. Ali, A. Nazir, and S. Kamal, Social Media Competitive Analysis of Shoe Brands on Customer Experiences, vol. 932. Springer Singapore, 2019.
W. He, S. Zha, and L. Li, “Social media competitive analysis and text mining: A case study in the pizza industry,” Int. J. Inf. Manage., vol. 33, no. 3, pp. 464–472, 2013, doi: 10.1016/j.ijinfomgt.2013.01.001.
B. Liu, S. G. Cao, and W. He, “Distributed Data Mining for E-Business. Information Technology & Management,” vol. 12(1), pp. 1–13, 2011.
J. Jin, P. Ji, and R. Gu, “Identifying comparative customer requirements from product online reviews for competitor analysis,” vol. 49, pp. 61–73, 2016.
H. Wang, S. Gao, P. Yin, and J. N. . Liu, “Competitiveness analysis through comparative relation mining: evidence from restaurants’ online reviews,” Manag. data Syst., vol. 117 (4), pp. 672–687, 2017.
Y. Kim, R. Dwivedi, J. Zhang, and S. . Jeong, “Competitive intelligence in social media twitter: iphone 6 vs. Galaxy S5,” vol. 40 (1), pp. 42–61.
S. Sulova, L. Todoranova, B. Penchev, and R. Nacheva, “Using text mining to classify research papers,” Int. Multidiscip. Sci. GeoConference Surv. Geol. Min. Ecol. Manag. SGEM, vol. 17, no. 21, pp. 647–654, 2017, doi: 10.5593/sgem2017/21/S07.083.
N. Li and D. D. Wu, “Using text mining and sentiment analysis for online forums hotspot detection and forecast,” Decis. Support Syst., vol. 48, no. 2, pp. 354–368, 2010, doi: 10.1016/j.dss.2009.09.003.
B. Pang and L. Lee, “A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts,” pp. 271–278, 2004, doi: 10.3115/1218955.1218990.
I. Rasila, U. Ristian, J. Rekayasa Sistem Komputer, and F. H. MIPA Universitas Tanjungpura Jl Hadari Nawawi, “Implementasi Metode Naive Bayes Classifier Pada Sistem Pengklasifikasi Berita Otomatis Berbasis Website (Studi Kasus: Berita Lokal Dari Mediamassa Online Kalimantan Barat),” Coding J. Komput. dan Apl., vol. 07, no. 2, pp. 49–60, 2019.
D. M. Blei, “Probabilistic topic models,” Commun. ACM, vol. 55, pp. 77–84, 2012.
K. Stevens, P. Kegelmeyer, D. Andrzejewski, and D. Buttler, “Exploring topic coherence over many models and many topics,” EMNLP-CoNLL 2012 - 2012 Jt. Conf. Empir. Methods Nat. Lang. Process. Comput. Nat. Lang. Learn. Proc. Conf., no. July, pp. 952–961, 2012.
J. Yang, P. Xiu, L. Sun, L. Ying, and B. Muthu, “Social media data analytics for business decision making system to competitive analysis,” Inf. Process. Manag., vol. 59, no. 1, p. 102751, 2022, doi: 10.1016/j.ipm.2021.102751.
How to Cite
Copyright (c) 2022 International Journal of Sciences: Basic and Applied Research (IJSBAR)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who submit papers with this journal agree to the following terms.