Publication Search

The increasing volume of online hotel reviews provides valuable insights into customer perceptions but poses challenges for manual analysis due to its unstructured nature. This study aims to compare the performance of Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Transformers (BERT) in hotel review sentiment analysis. A total of 20,491 TripAdvisor hotel reviews were classified into three sentiment categories: negative, neutral, and positive. The research methodology includes text preprocessing, stratified data splitting, class imbalance handling using Random Over-Sampling, tokenization, and supervised model training. Model performance was evaluated using a confusion matrix and classification metrics. The results indicate that BERT outperforms RNN, achieving an accuracy of 80.54%, while RNN reached 62.21%. BERT demonstrated superior capability in capturing contextual and semantic information in hotel reviews. These findings suggest that transformer-based models are more effective for sentiment analysis of complex textual data in the hospitality domain and can support data-driven service improvement strategies.    

Gestational Diabetes Mellitus (GDM) is a pregnancy-related metabolic disorder that poses health risks to both mother and fetus if not detected early, requiring accurate prediction methods for early screening and clinical decision-making. This study applies the Random Forest algorithm to detect GDM risk using clinical data from the Pima Indian Dataset. Data preprocessing included handling missing values, standardization, feature engineering, and a 70:30 train–test split. Two models were developed: a baseline and an optimized model using GridSearchCV hyperparameter tuning, validated with 5-fold cross-validation. Performance was assessed using a classification report, confusion matrix, and ROC–AUC. Results show that the optimized model outperforms the baseline, achieving 88% accuracy, an AUC of  93%, and average recall of 81%–85%. Compared to previous studies, this approach demonstrates improved predictive performance. The findings indicate that combining Random Forest with comprehensive preprocessing, feature engineering, and model optimization is effective and feasible for developing a medical decision support system for early GDM risk screening.

Abstract: The rapid diffusion of Generative Artificial Intelligence (AI) has intensified public debate regarding its benefits, risks, and societal implications. This study investigates public sentiment and thematic structures surrounding Generative AI by analyzing Twitter discourse as a representation of large-scale, real-time public perception. The research addresses two main problems: how public sentiment toward Generative AI is distributed and what dominant themes shape this perception. Accordingly, the objective is to map both emotional polarity and thematic narratives embedded in social media conversations. A computational mixed-methods approach was employed using a dataset of 12,470 tweets collected on 17 December 2024. Sentiment classification was conducted using a transformer-based DistilBERT model, while semantic representations were generated with Sentence-BERT. Topic modeling was performed using BERTopic, integrating HDBSCAN clustering and class-based TF-IDF to extract coherent and interpretable topics. Human-in-the-loop validation supported the interpretive robustness of topic labeling. The findings reveal that public sentiment toward Generative AI is predominantly positive (41.8%), particularly in relation to productivity enhancement, education, and creative applications. Neutral sentiment (31.4%) reflects informational discourse, while negative sentiment (26.8%) centers on ethical concerns, privacy risks, misinformation, and AI hallucinations. Seven dominant topics were identified, with clear topic–sentiment alignment showing optimism in utility-driven themes and skepticism in ethics- and risk-related discussions. In conclusion, public perception of Generative AI is dualistic—characterized by strong enthusiasm alongside persistent caution. These results provide empirical insights for AI governance, responsible innovation, and future research on socio-technical impacts of Generative AI. *    

Manual quality assessment of Platelet Concentrate (TC) is highly subjective and inconsistent, necessitating an objective, automated classification system. This study aims to develop a computationally efficient, low-cost model for TC quality classification using Histogram Features extracted from grayscale images combined with the K-Nearest Neighbor (KNN) algorithm. The methodology employed critical preprocessing steps, including StandardScaler for normalization and SMOTE for balancing the training data, followed by optimization across K=1 to K=30. The optimal model achieved a maximum accuracy of 69.23% at K=6, with an F1-Score of 71.43%, confirming robust performance on the imbalanced testing set. The results validate the effectiveness of the Histogram-KNN approach as a consistent and reliable decision support system for rapid TC quality screening in resource-limited settings.

The development of social media platforms like TikTok has created new spaces for digital economic activities, including the practive of thrifting, which has now become a trend among the public. However, government policies that block these activities have sparked various public reactions. This study aims to analyze public sentiment regarding the issue of thrifting bans on the TikTok platform using the Bidirectional Long Short-Term Memory (Bi-LSTM) method. This method was chosen because it can understand text context from both directions, allowing it to capture deeper semantic meaning. The dataset consist of 4,000 TikTok user comments collected through a crawling process. The research stages include data preprocessing, sentiment labeling, splitting training and test data, training the Bi-LSTM model, and evaluating performance using accuracy, precision, recall, and F1-score metrics. The research results show that the Bi-LSTM model achieved an accuracy of 86.15%, with stable classification performance and minimal error rate. These findings indicate that Bi-LSTM is effective for sentiment analysis of public opinions on Indonesian language social media, particularly on context specific policy issues. Further development can be carried out by adding pre-trained embeddings or attention mechanisms to improve the model’s performance.

Tourism is one of the sectors that plays an important role in boosting economic growth through travel activities and destination exploration. Tourists' preferences for nature-based tourism options, such as mountain hiking or beach tourism, are influenced by various factors, ranging from personal experiences and recreational interests to social characteristics. Therefore, a technology-based approach is needed to predict destination choice tendencies more accurately. As artificial intelligence technology develops, deep learning methods have been widely used in classification processes due to their ability to process large amounts of data and recognize complex patterns. In this study, a Multilayer Perceptron (MLP) model is used to classify tourists' preferences between mountain or beach destinations based on a survey dataset. The research stages include data processing, data splitting using a train-test split, model training, and performance evaluation using accuracy, precision, recall, and F1-score. The test results show that the MLP model is capable of achieving an accuracy rate of 99%, confirming that deep learning methods are effective in automatically mapping tourism preference trends. This research is expected to serve as a basis for the development of more personalized travel destination recommendation systems, as well as to support tourism management in formulating targeted promotional strategies.

Social care values ​​are moral principles that emphasize empathy, altruism, solidarity, mutual cooperation, justice, and tolerance in social life. These values ​​form the foundation for individuals to understand the feelings of others, help selflessly, cooperate, be fair, and respect differences. This study aims to describe the representation of social care values ​​in Wattpad short stories in the family drama genre, identify the most dominant values ​​and the context in which they emerge, and explain the relevance of these findings to learning and character development in students. The study used a descriptive qualitative method because it focuses on the meaning of the text, rather than quantitative measurement. Data were collected through listening and note-taking techniques by carefully and repeatedly reading the short stories to identify sections of the text that contain social care values. Data included words, phrases, sentences, dialogue, and narratives that depict character actions, conflicts, or interactions reflecting empathy, altruism, solidarity, mutual cooperation, justice, and tolerance. All quotations were recorded on a coding sheet to organize the data systematically. Data analysis was conducted using the Miles and Huberman technique, which includes data reduction, classification, and interpretation. In the reduction stage, relevant data was selected and then grouped according to social awareness value categories. Next, interpretation was conducted to explain the representation of these values ​​in the storyline and relationships between characters. 

This Community Service activity reflects university students' social concern for their environment, particularly in elementary education. The activity was conducted at SDN 032 Tarakan to provide students with an understanding of the differences between needs and wants. The method used was face-to-face socialization, interactively designed through simple material delivery, ice-breaking, and an image classification game. The results showed high student enthusiasm and their ability to correctly classify most of the provided images into 'needs' and 'wants'. This activity not only enriched students' knowledge but also trained critical thinking skills in setting priorities. It is hoped that similar activities can be continued to foster economic literacy from an early age among elementary school students.

Hijaiyah letters have varying shapes, and some of them are very similar, often causing errors in the manual character recognition process. This study aims to classify Hijaiyah letters based on digital images using the Convolutional Neural Network (CNN) method. This method was used in this study with a dataset consisting of 28 letter classes and a total of 4,480 images obtained from various public sources and private data. All images underwent a preprocessing stage that included labeling, resizing, normalization, and augmentation, then were divided into three parts, namely training data, validation data, and test data with a ratio of 70:20:10. The training process was carried out using the Python programming language with the help of the TensorFlow and Keras libraries on the Google Colab platform. The test results showed that the CNN model achieved an accuracy of 97.10%, with an average precision, recall, and F1-score of 0.97, respectively. Classification errors only occurred in letters that had similar shapes, such as Syin and Sin. Based on these results, the CNN method proved to be effective, efficient, and accurate in recognizing Hijaiyah letter image patterns, so it can be used as a basis for developing classification models with higher accuracy in the future.  

Waste has become a serious environmental problem in Indonesia, which continues to increase along with population growth. The issue of waste management poses serious challenges for the environment, especially in the process of separating organic and inorganic waste. In the field of computer vision, recognising the type and shape of waste through camera images remains a challenge due to variations in shape, colour, and complex lighting conditions. Therefore, this problem utilises Deep Learning technology, which is expected to be widely applied in Indonesia, especially in large cities with high waste volumes. This study aims to distinguish between organic and inorganic waste using the Convolutional Neural Network (CNN) method based on digital images. The developed CNN model was trained to recognise the visual patterns of each type of waste and tested to measure its accuracy. The test results show that the CNN-based classification system is capable of achieving an accuracy rate of 95%, thus proving the effectiveness of this method in supporting artificial intelligence-based automatic waste sorting systems.

The rapid expansion of e-commerce in Indonesia has resulted in a significant rise in the number of customer reviews, which serve as a valuable source of insight for understanding consumer satisfaction. This study aims to classify or identify sentiments from product reviews on the Tokopedia platform into three categories, using the Support Vector Machine algorithm. The classification method data were ethically collected through web scraping and include review text, ratings, and the number of “likes.”  The preprocessing stage involved several NLP techniques such as pre-procesesing data representation was generated using the Term Frequency–Inverse Document Frequency method, while the issue of class imbalance was addressed using the Synthetic Minority Over-sampling Technique.  Based on the test results, the SVM model achieved an accuracy of 79.48% on the test data using a linear kernel, showing the best performance in classifying positive sentiments. However, the classification of neutral and negative sentiments still requires improvement. This study demonstrates that the combination of the TF-IDF method, additional numerical features, and data balancing techniques can produce an an efficient sentiment analysis model within the e-commerce domain.

The growing demand for energy-efficient and intelligent thermal systems has driven significant advancements in adaptive compressor design. This paper presents a comprehensive literature review on the development of AI-based compressor systems, with a specific focus on enhancing efficiency under partial-load conditions and optimizing the utilization of residual energy. Through the synthesis of five recent high-impact studies (2020–2025), we examine the application of deep reinforcement learning (DRL), hybrid evolutionary algorithms, and neural network surrogate modeling in compressor optimization. Key findings indicate that model-based DRL combined with surrogate CFD can achieve up to 8% efficiency gains at off-design conditions. Hybrid approaches integrating Genetic Algorithms (GA) with DRL reduce optimization time by 30% while improving pressure ratios. Neural network surrogates provide high-speed, real-time performance predictions with less than 1% error, enabling mass iterative design. Furthermore, intelligent load classification using radial basis function networks (RBFN) allows adaptive response to varying operating conditions with over 95% accuracy. Collectively, these methods form a framework for intelligent, self-optimizing compressor systems capable of real-time adaptation and energy recovery. The results suggest that AI-enhanced adaptive compressors represent a transformative direction for energy-sensitive sectors, including HVAC, power generation, and sustainable industry.

Penelitian ini bertujuan untuk mengembangkan sistem pendukung keputusan yang dapat membantu tim Marketing Officer (MO) PT. Alvarel Technology Innovation dalam menentukan status pelanggan secara objektif dan terstruktur. Sistem ini dirancang menggunakan kombinasi metode Analytical Hierarchy Process (AHP) dan Weighted Sum Model (WSM). Metode AHP digunakan untuk menentukan bobot kriteria yang meliputi Potensial Pasar, Urgensi, Finansial, serta Hubungan dan Reputasi, dengan memastikan konsistensi matriks perbandingan berpasangan. Hasil pembobotan kemudian digunakan dalam metode WSM untuk melakukan perhitungan skor total pelanggan dan menyusun pemeringkatan status berdasarkan nilai tertinggi hingga terendah. Data penelitian diperoleh dari catatan internal perusahaan dan wawancara dengan Marketing Officer, dengan jumlah sampel 30 pelanggan. Hasil pengujian menunjukkan bahwa sistem dapat menghasilkan peringkat status pelanggan dalam lima kategori, yaitu potensial, prospek, pending, pasif, dan skip. Temuan utama memperlihatkan bahwa kategori prospek memperoleh skor tertinggi dan menjadi prioritas tindak lanjut. Dengan demikian, sistem pendukung keputusan berbasis AHP–WSM ini mampu mengurangi subjektivitas, meningkatkan efisiensi, serta memberikan rekomendasi yang lebih akurat dan terukur untuk mendukung pengambilan keputusan strategis perusahaan dalam pengelolaan pelanggan.

This research is based on the awareness that music functions both as an artistic expression and as a cosmological representation embedded within the cultural structures of traditional societies. The Siwaluh Jabu traditional house in Lingga Village, North Sumatra, was selected as the object of study to examine the relationship between music and the cosmological views of the Karo people. The purpose of this study is to reveal the meaning of music within cultural practices and rituals carried out in the Siwaluh Jabu House, as well as to explore musical elements that reflect the continuity between humans, ancestors, and the universe. This research employs a qualitative approach, with data collected through literature review, participatory observation, and interviews with traditional leaders and local artists. The data analysis was conducted through data reduction, classification, data presentation, and drawing of conclusion. The results of the study show that music both the vocal mantra “ole…ah…ole” and the Gendang Lima Sendalanen ensemble contains symbolic values that interpret wood as a natural element, sustain social connections between groups, and reinforce the social system embedded in the spatial organization of the Siwaluh Jabu traditional house. Music serves as a medium of spiritual and cultural communication that unites the physical and metaphysical dimensions of life. The implications of this research enrich the perspective of music culture and emphasize the importance of preserving traditional music as a local knowledge system integrated with the cosmology of the Karo people.

The growth in the number of vehicles in Surabaya has led to increased traffic congestion, particularly on the Perak Timur–Perak Barat road section, which serves as a major distribution route to the port and industrial areas. Problems arise at U-Turn points, where vehicle accumulation hampers traffic flow. This study analyzes traffic volume, travel time, queue length, and queue ratio at two U-Turn points on this section. The method used was a field survey with direct observation of vehicle volume every 15 minutes, vehicle classification, and queue length. Traffic volume was calculated using the Passenger Car Equivalent (PCE) factor based on the 1997 MKJI standards. The study results show that at Point 1, east–west direction, the highest queue ratio occurred on Tuesday from 11:00 to 12:00 (p = 4.84), while the lowest was on Sunday from 06:00 to 07:00 (p = 0.21). At Point 2, west–east direction, the highest queue ratio occurred on Tuesday from 08:00 to 09:00 (p = 6.18), and the lowest from 06:00 to 07:00 (p = 0.41). These findings indicate that during peak hours, traffic congestion increases (p > 1), causing long queues, particularly in the west–east direction in the morning. The performance of the U-Turn on the Perak Timur–Perak Barat road section needs improvement, with recommendations such as temporarily closing U-Turns during high volumes, providing alternative U-Turn lanes, and adding signs to minimize the potential for vehicle conflicts.

This research proposes an alternative model for predicting the plasticity potential of clay soils, updating the previous model developed by Firincioglu and H. Bilsel. The alternative lies in the use of the fine fraction content (FC) as the predictive variable, replacing the percentage of sand fraction content (SC) previously suggested. The analysis was conducted on 61 low-plasticity clay (CL) soil samples, classified using the Casagrande and Moreno-Maroto systems, by examining the relationship between consistency limits (LL, PI), grain fractions (sand, silt, clay), and related parameters (FC, sand-silt-clay spectrum, and sand fraction ratio). The correlation analysis results show significant findings, including a strong positive correlation between sand content and the sand ratio (SR), as well as a negative correlation between sand content and FC, and between FC and SR. The performance of the substitute Casagrande quadratic model [2] reveals the best predictive accuracy among the proposed models ( [1], R² =0.90; [3], R²  0.89; [4], R² =0.43; [5], R² =0.93; [6], R² =0.93; [7], R² =0.89; [8], R² =0.89), with the highest R2 value of 0.93, MSE of ≈4.01, and MAE of ≈1.44–1.47. The equation is .

This study aims to analyze user sentiment toward the integration of Artificial Intelligence (AI) in online learning platforms, which are increasingly expanding in the digital era. With the growing use of AI technologies in education—such as learning chatbots, material recommendation systems, and automated assessments—it is essential to understand users’ perceptions and reactions to these implementations. The research employs sentiment analysis based on text mining using user review data collected from various online learning platforms. The analysis process includes data preprocessing, sentiment classification using machine learning algorithms, and interpretation of results based on the proportion of positive, negative, and neutral sentiments. The findings indicate that most users express positive sentiments toward AI integration, as it enhances learning efficiency and personalization. However, some users raise concerns regarding data privacy and the lack of human interaction. This study is expected to serve as a reference for educational platform developers to design AI systems that are more adaptive, transparent, and user-centered

Pancur Batu District, as one of the areas in Deli Serdang Regency, is experiencing the dynamics of regional development and pressure on land. The total area of ​​Pancur Batu District in Deli Serdang Regency is 122.53 km2. Information on the current land use conditions is essential to support spatial planning and sustainable development policy making. This study aims to identify, map, and analyze the distribution of Sustainable development. This study aims to identify, map and analyze the distribution of land use in Pancur Batu sub-district by utilizing remote sensing technology. The method used is visual interpretation and on-screen digitization using high-resolution satellite imagery from Google Earth in 2024. Land use classification is divided into several main classes, such as settlements, open land and road networks. The main result of this study is a land use map of Pancur Batu sub-district with a 1: 63,360 map that presents a special distribution of each land use class. From the results of the map analysis, it is known that land use is dominated by open land. Meanwhile, identified residential areas are growing rapidly along the main road network. The resulting map can be accurate and up-to-date basic data for the Deli Serdang district government for monitoring, evaluating land suitability, and controlling space use in Pancur Batu sub-district.

In the era of digital transformation, modern, systematic, and integrated archive management has become a crucial element in creating effective, efficient, and accountable education governance. Office Management and Business Services (MPLB) teachers in East Java still face obstacles in implementing technology-based archive management due to limited digital literacy, lack of supporting facilities, and minimal ongoing training relevant to 21st-century needs. This Community Service (PKM) activity aims to improve the professional competence of MPLB teachers in modern archive management through interactive workshop-based training, intensive mentoring, and direct simulation of the use of digital archiving applications. The implementation methods included participant needs analysis, problem-solving-based module development, digital archive management practice using a cloud system, and pre-test and post-test-based evaluation to measure competency improvement. The results of the activity showed an average increase in participant understanding of 42%, a 58% increase in operational skills in using archiving applications, and a 35% increase in archive management time efficiency. In addition, teachers are able to implement an electronic file classification system in schools and build a database of digitized documents. These activities strengthen transparent and sustainable educational administration, as well as supporting the realization of inclusive and globally competitive education in line with the Asta Cita vision towards Indonesia Emas 2030.

This study aims to determine the accounting treatment for fixed assets at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province, and to determine whether the accounting treatment for fixed assets at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province, complies with PSAP No. 07 concerning Fixed Asset Accounting. This study used a qualitative descriptive research method, using triangulation (a combination of observation, interviews, and documentation) as data collection techniques at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province. The results of this study indicate that the accounting treatment for fixed assets at Dr. Adhyatma Regional General Hospital, MPH, Central Java Province, in terms of classification, recognition, measurement, cost components, post-acquisition expenditures, depreciation, retirement, and disposal, complies with PSAP No. 07 concerning Fixed Asset Accounting. Disclosure of fixed assets regarding the reconciliation of the recorded amount at the beginning and end of the period and depreciation information including the depreciation value, gross recorded value and accumulated depreciation at the beginning and end of the period is in accordance with PSAP Number 07 of 2010 concerning Fixed Asset Accounting. However, for the basic information on the valuation used to determine the recorded value, depreciation information in the form of the depreciation method used and the useful life or depreciation rate used is not in accordance with PSAP Number 07 of 2010 concerning Fixed Asset Accounting.