Available online at www.HighTechJournal.org HighTech and Innovation Journal Vol. 4, No. 2, June, 2023 453 ISSN: 2723-9535 BERT: A Review of Applications in Sentiment Analysis Md Shohel Sayeed 1* , Varsha Mohan 1 , Kalaiarasi Sonai Muthu 1 1 Faculty of Information Science and Technology, Multimedia University, 75450 Melaka, Malaysia. Received 14 February 2023; Revised 19 May 2023; Accepted 24 May 2023; Published 01 June 2023 Abstract E-commerce reviews are becoming more valued by both customers and companies. The high demand for sentiment analysis is driven by businesses relying on it as a crucial tool to improve product quality and make informed decisions in a fiercely competitive business environment. The purpose of this review paper is to explore and evaluate the applications of the BERT model, a Natural Language Processing (NLP) technique, in sentiment analysis across various fields. The model has been utilized in certain studies for various languages, restaurant businesses, agriculture, Automated Essay Scoring (AES), Twitter, and Google Play. The BERT model's fine-tuning steps involve using pre-trained BERT to perform various language understanding tasks. Text pre-processing is conducted to clean up the data and convert it to numbers before feeding it into BERT, which generates vectors for each input token. We found that BERT outperformed the norm on a range of general language understanding tasks, including sentiment analysis, paraphrase recognition, question- answering, and linguistic acceptability. The detection of neutral reviews and the presence of false reviews in the dataset are two problems that have an impact on the model's accuracy. Training is also slow because it is huge and there are many weights to update. Additional research could be conducted to improve the BERT model's accuracy by constructing a false review categorization model and providing more training to the model in recognizing neutral reviews. Keywords: Natural Language Processing; BERT; Fine-Tuning; Machine learning; Sentiment Analysis. 1. Introduction The word "e-commerce" refers to the exchange of goods and services over the internet. It offers a variety of tools, guidelines, plus resources for both buyers and sellers, including cash on delivery, mobile shopping alternatives, and encryption for online payments [1]. Consumers and businesses alike are valuing reviews more and more. Consumers may use internet reviews to assist their decision about whether to buy a product. Reviews often include text and a rating. The score, which is often a number from 1 to 5, with 1 being the worst and 5 being the best, is the reviewer's reflection on the text. As illustrated in Figure 1, a survey by the marketing company Fan & Fuel (2023) found that 92% of consumers are swayed by the lack of online evaluations. This group expressed substantial uncertainty about what would happen next; 35% said they were less likely to buy, 32% said they would postpone their purchase until they could do more study, 23% said it would be challenging to make their decision, and 2% said they would simply not buy the product or service [2, 3]. * Corresponding author: shohel.sayeed@mmu.edu.my http://dx.doi.org/10.28991/HIJ-2023-04-02-015  This is an open access article under the CC-BY license (https://creativecommons.org/licenses/by/4.0/). © Authors retain all copyrights. Review Article