This research is motivated by the motivation to capture customer experience in purchasing rice products in the Shopee marketplace. The method used is Latent Dirichlet Allocation and analyzed based on several rating categories, namely low rating (negative sentiment), medium rating (neutral sentiment) and high rating (positive sentiment). The results of this study indicate that customer reviews of purchasing rice products in the shopee marketplace have a dominant positive sentiment, followed by negative and neutral sentiment. Negative sentiment consists of the words with the most frequency namely "quality", "delivery", "price" as well as negative words such as ticks and leaks. Positive sentiment consists of the words that appear the most, namely "price", "buy", "quality", "send", "good". The selection results based on the coherence value are visualized with a total of 3 topics, namely those related to the topics of rice quality and price, taste and quality, price and delivery.
Procurement of books is one of the jobs of a librarian, both in university libraries and public libraries, the procurement of books itself has several stages and one of them is determining the priority books to be purchased first and also recommendations for additional or other supporting books. In one of the business college libraries in the city of Bogor, there are still obstacles in determining the title of the book to be purchased due to the workings and the assessment process which is still done manually and repeatedly, therefore in this study, an application was made that can determine the title. Books that can be prioritized to be purchased first and also other alternatives in the form of a ranking system that uses the title of the book as an alternative and also some special criteria used that have been approved by the relevant library such as the year of publication, the availability of complete books, and also book reviews. This research was conducted to make it easier for library staff and also to increase the effectiveness of determining the priority book titles in one application count. And also a feasibility test has been carried out on the application made, with a feasibility value of 85%, which means the application made is very feasible and has also been tested for accuracy using the formula confusion matrix with an accuracy value of 100%.
Public opinion, whether positive, negative, or neutral, regarding a particular policy or phenomenon in society, is a valuable thing to analyze through a method known as sentiment analysis. The case in this study is the decline in grain prices in early to mid-2021. This study aims to determine the percentage of sentiment polarity that appears when associated with the keyword price of grain and determine the level of accuracy of sentiment class predictions using the Naïve Bayes method. The results showed that the largest percentage of sentiment was negative as much as 46.30%, neutral 32.70% and positive as much as 20.99%. The results of the wordcloud also show that twitter users link the issue of grain prices to rice imports, the role of the government and fertilizers. The results of the classification show a fairly good accuracy value of 67.32%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.