Customer feedback in the modern era like today is mostly presented in the form of digital reviews, including customer feedback at an inn or hotel, customer feedback is very valuable data where from this data the management can find out, identify and analyze the customer experience and what they need. With customer feedback in the form of digital reviews, it will allow a lot of data that can be obtained by hotel management and will provide many benefits if the data is processed correctly. To take advantage of large  text review data, a combination of data mining and natural language processing techniques was chosen to process text in depth and efficiently.  Text mining in the form of creating an opinion mining model using the Naïve Bayes classification algorithm is applied to find information and measure the main sentiments expressed in the reviewed text dataset, then the application of K-Means text grouping aims to group texts and get information about the main topics discussed from the content of the review dataset text in each group . By applying the constructed sentiment analysis model, approximately 90.90% accuracy results were obtained in reading texts and measuring sentiments related to hotel customer feedback data.

The purpose of this study was to compare the accuracy performance of the K-Means and DBScan algorithms in clustering product reviews. This comparison evaluated to determine which algorithm is better in terms of accuracy. The two algorithms were chosen because they have different methods of clustering, K-Means uses centroid-based while DBScan uses density-based. Text clustering results can be implemented on e-commerce platforms, marketplaces or product review platforms. This can help customers in deciding what product they will buy. One of the factors that customers have difficulty in determining what product they will buy is the number of reviews that each product has, and the difficulty in concluding the advantages of each product that will be matched their needs or desires. With text clustering, it can be easier and faster for customer to determine whether the product is worth buying or not based on the product reviews they read. The data set used in this study is a review of the Cetaphil Facial Wash product from the Female Daily website. Firstly, data set goes through the Text Pre-Processing stage; then it will be clustered using two algorithms, K-Means and DBScan. After that, the results of the clustering of the two algorithms calculated for their accuracy performance and the performance results obtained. From the results of this study, it concluded that, in the review clustering of Cetaphil Facial Wash products, DBScan has 99.80% accuracy, which higher to compare with K-Means with only has 99.50% accuracy.

No abstract

No abstract

Penanganan pengaduan ketenagakerjaan merupakan salah satu faktor kinerja Disnakertrans. Kinerja ini berhubungan dengan keputusan yang harus diambil   untuk menentukan kebijakan agar pelanggaran norma ketenagakerjaan dapat berkurang. Pengambilan keputusan ini akan lebih mudah jika data pengaduan dapat direkapitulasi secara cepat dan akurat. Rekapitulasi ini akan menjadi alat pantau pimpinan dalam melihat laporan kemajuan status pengaduan yang masuk. Akan tetapi proses administrasinya yang manual membuat rekapitulasinya semakin lambat. Oleh karena itu, penelitian ini akan memodelkan sistem digitalisasi pelaporan pengaduan dengan memanfaatkan OCR dan ekstraksi informasi serta memodelkan visualisasi hasil rekapitulasi menggunakan Business Intelligence. Dengan dibuatnya model ini, diharapkan kinerja Disnakertrans dalam menyelesaikan pengaduan ketenagakerjaan lebih efektif