This research uses a deep learning-based sentiment analysis approach with several main stages, namely data collection, preprocessing, model preparation, and model building. In addition, this research also evaluates the impact of data splitting techniques on the model's performance during the training process.The evaluation results show that the LSTM-GRU model achieved the best performance on the character aspect, with an F1-score of 0.72 in the 90:10 splitting scenario. Meanwhile, the lowest F1-score was found in the editing aspect, with a value of 0.51 in the 80:20 splitting scenario. These findings indicate that the model is more effective in recognizing sentiment in narrative aspects compared to technical aspects. Furthermore, the data splitting technique significantly influences model performance, both in determining accuracy levels and in optimizing the model's effectiveness in identifying sentiment patterns more accurately.

Hotel booking cancellations pose significant challenges to the hospitality industry, affecting revenue management, demand forecasting, and operational efficiency. This study explores the application of machine learning techniques to predict hotel booking cancellations, leveraging structured data derived from hotel management systems. Various classification algorithms, including Random Forest, XGBoost, and LightGBM were evaluated to identify the most effective predictive model. The findings reveal that XGBoost model outperforms other models, achieving F2-score of 0.7897. Key influencing factors include deposit type, total number of special requests, and marketing segment. The results underscore the potential of predictive modeling in optimizing hotel revenue strategies by enabling proactive measures such as dynamic pricing, targeted customer engagement, and improved overbooking policies. This study contributes to the ongoing advancements in data-driven decision-making within the hospitality industry, offering insights into how machine learning can mitigate financial risks associated with booking cancellations.

The application of Virtual Reality (VR) based on the Metaverse in education is an innovation that can enhance the quality of learning by providing a more interactive and immersive learning experience. This article discusses the development of VR-based learning integrated with the Metaverse using the ADDIE model (Analysis, Design, Development, Implementation, Evaluation). Through the stages of analysis, design, development, implementation, and evaluation, VR and Metaverse-based learning can be tailored to students' needs, creating a more flexible and collaborative learning experience. The use of this technology allows students to learn independently or in groups, while improving practical skills and creativity. This study shows that by applying the ADDIE model, VR and Metaverse-based learning can be more effective in increasing student motivation and learning outcomes, addressing the challenges of education in the future.

The e-guestbook application is an application used to record and process guest data arriving at an institution. The quality of the e-guestbook application system needs to be measured to determine the level of quality and user satisfaction with the application. This study aims to analyze the quality measurement of the e-guestbook application using the Six Sigma method at the South Sumatra High Prosecutor's Office. The Six Sigma method was chosen because it can identify and measure Critical to Quality (CTQ), thereby improving the quality of the application. The research results show that the sigma value of the e-guestbook application is 4.16, which means the quality of the application is very good. However, there are several aspects that need improvement, namely the ease of use of the application, the accuracy of the information, and the availability of application features. The recommended improvements are enhancing the user interface, validating input data, and adding a report printing feature. The application of the Six Sigma method has proven effective in measuring and improving the quality of the e-guestbook application at the High Prosecutor's Office of South Sumatra

This study analyzes demographic data from regencies/cities in Central Kalimantan Province, including population, population growth rate, population percentage, population density per km², and sex ratio. The results of the analysis show significant differences between regencies/cities, with population growth rates ranging from 0.98% to 1.97% per year. The highest population density was recorded in East Barito, while Lamandau had the lowest density. The sex ratio tends to show a male dominance, with Lamandau having the highest ratio. These findings provide an overview of the challenges and opportunities in development planning, as well as the need to design policies that are in accordance with the demographic characteristics of each region. A deeper understanding of this data is expected to support more effective policies in population management and development in Central Kalimantan.

Due to the variety of types of flowers that exist and having and tracking each variety, making plant lovers and cultivators difficult to distinguish in determining the type of flower, it takes a very long time to find out the type of flower if you only rely on the five senses. With the application of the K-Nearest Neighbor algorithm and feature extraction of color and texture, it is very helpful in image processing to identify flowers more easily and shorten the time, with the greatest accuracy of 71% using the K-7 value, the flower was successfully carried out.

The rapid advancement of technology in the field of education has provided numerous opportunities to enhance the learning experience. This study focuses on the development of an Android-based learning media for introducing rare plants, specifically designed for elementary school students. The application utilizes Unity 3D to create an engaging and interactive learning environment. By integrating English language learning with botany education, the application aims to enrich students' knowledge about rare plants while simultaneously improving their English language skills. This phase is followed by the design and development stages, where Unity 3D is used to create 3D models and interactive features. The application is designed to provide an interactive and enjoyable learning experience for elementary school students to explore rare plants. By using the Android platform and Unity 3D technology, the application allows students to discover various plant names in English. Results from a trial with 20 respondents on the Android-based learning media for introducing rare plants showed that 49.35% strongly agreed, 49.25% agreed, 1.37% were unsure, 0% disagreed, and 0% strongly disagreed.

In the current era of globalization and technology, computers, RFID are examples of information technology tools that are indispensable for meeting human needs in almost every aspect of life, including the management of infrastructure and equipment lending.According to direct research at Widya Praja Ungaran Vocational School, there are only two workers who handle facilities and infrastructure. In carrying out their work assignments, they still experience difficulties. Excess workload and the process of borrowing tools that still lacks a sense of responsibility, so that the results of the work are not maximized.The existence of increasingly sophisticated technology, the management of infrastructure and equipment lending can be done with the help of technological tools that will be implemented in this school. This research aims to make it easier to administer, because this school has not yet added a new workforce.This research can be designed with the help of software (Bootstrap, MySql), programming (PHP, Arduino IDE) and equipment (NodeMCU ESP8266, RFID, LCD, I2C, buzzer, power supply, breadboard, jumper cables, resistors, LEDs) to provide data information. more accurate, effective, efficient and provide a good working atmosphere in this school. It is hoped that this research can reduce work overload and create a sense of responsibility in borrowing equipment, using local networks (wifi / handphone) and computers or laptops, with the research method used is research and development (R&D).

This research aims to design a web server-based heart rate monitoring system, which enables real-time heart rate monitoring from a remote location. The system utilizes a heart rate sensor connected to a microcontroller to measure and transmit heart rate data to a web server via an internet connection. The data obtained can be accessed directly by the user through a web-based interface, thus facilitating the monitoring of individual health conditions in an efficient manner. In addition, the system is equipped with a notification feature that alerts the user if any irregularities in the heart rate are detected, such as beating too fast or slow. As such, the system has the potential to increase alertness and speed up medical action if needed. The development of this system shows significant potential in supporting technology-based health applications, both for personal use and in a broader healthcare context. It is hoped that the system can contribute towards the development of more integrated and accessible health monitoring solutions.
 
 
 

Computer vision technology has advanced rapidly and made significant contributions across various fields, including object identification in images. This study aims to develop a computer vision-based system to identify fruit types from images. A machine learning model is applied using a dataset of fruit images to train the system for accurate fruit recognition. The primary processes include data acquisition, image preprocessing, feature extraction, model training, and performance evaluation. The results demonstrate a high level of accuracy in identifying specific fruit types, showcasing the potential of this technology in agricultural and commercial applications.