Publication Search

Digital documents have become an essential medium for storing, managing, and distributing information in various sectors. Nevertheless, the risk of document alteration and forgery requires an effective mechanism to verify document authenticity. This research focuses on the implementation of Base64 and Pepper methods in a QR Code-based document verification system. The system was developed following the Waterfall software development model, which consists of requirement analysis, system design, implementation, and testing stages. A web-based application was created using PHP and MySQL. Verification tokens were produced from document identity data combined with a Pepper value, encoded using Base64, and embedded into QR Codes attached to PDF documents. During verification, the QR Code is scanned and the extracted token is compared with records stored in the database. Experimental results demonstrate that the proposed system is capable of verifying document authenticity accurately and efficiently. Furthermore, Black Box Testing confirmed that all implemented functions operated as expected. Therefore, the integration of Base64 and Pepper contributes to improving the security and dependability of digital document verification.

The development of social media, especially TWITTER, has become one of the main means for people to express opinions and criticism on various issues, including the performance of law in Indonesia. This study aims to analyze public sentiment towards the performance of law based on TWITTER user comments using the Naïve Bayes algorithm. The research data consists of 1004 comments collected from several videos related to legal topics. The analysis process includes the stages of data crawling, pre- processing (text cleaning, normalization, and tokenization), labeling sentiment into positive, negative, and neutral, and testing the Naïve Bayes model. The results show that the Naïve Bayes algorithm is able to classify sentiment with an accuracy level of 93.73%. The distribution of sentiment from 1004 comments shows that the majority of public opinion is (negative/positive/neutral), which indicates that public perception of the performance of law is still (critical/positive). These findings are expected to be input for related parties to understand public opinion and improve the quality of legal performance in

QRIS (Quick Response Code Indonesian Standard) has become a widely used national digital payment standard. User satisfaction with this service needs to be monitored continuously to ensure its sustainability. This study aims to predict the level of QRIS user satisfaction based on their experiences and perceptions expressed organically on the Twitter social media platform. The method used is sentiment analysis with the Naive Bayes classification algorithm implemented using RapidMiner software. The research data was obtained from Twitter user comments collected through web scraping techniques. The text data then went through a preprocessing stage that included cleansing, stopword filtering, stemming, and tokenizing to be prepared as features ready to be processed by the model. The data was divided into training (80%) and testing (20%) subsets for model training and validation. The results showed that the Naive Bayes model was able to predict user satisfaction sentiment with an accuracy of 80.99%. These findings indicate that the model is highly accurate in identifying satisfied comments and sufficiently sensitive in detecting dissatisfaction. This study concludes that sentiment analysis of Twitter UGC data using Naive Bayes is an effective and efficient approach for predicting QRIS user satisfaction in real time. The practical implication of this study is to provide an automatic feedback system for service providers to monitor public sentiment and take targeted corrective actions.

Social media has evolved into a significant platform where consumers freely express their opinions, experiences, and levels of satisfaction regarding various products, including those offered by Micro, Small, and Medium Enterprises (MSMEs). The comments and reviews shared by customers on these platforms contain diverse sentiments that can serve as valuable indicators of how consumers perceive product quality. Understanding these sentiments is crucial for MSME owners, as it allows them to evaluate their products and adapt to market expectations more effectively. This study aims to analyze customer sentiment toward MSME products on social media by utilizing the Naïve Bayes algorithm, a widely used classification method in text mining. The data used in this research consist of customer comments collected from various social media platforms. The research process involves several stages, including data collection, manual labeling of sentiments, text preprocessing (such as tokenization, case folding, and stopword removal), and splitting the dataset into training and testing subsets. Subsequently, the classification process is carried out using the Naïve Bayes algorithm to categorize sentiments into positive, negative, and neutral classes. The results of this study demonstrate that the Naïve Bayes method is effective in classifying customer sentiments with a satisfactory level of accuracy. These findings provide a comprehensive overview of consumer perceptions regarding the quality of MSME products. Furthermore, this research is expected to assist MSME business owners in understanding customer feedback more systematically and using it as a basis for improving product quality and enhancing customer satisfaction in a competitive digital marketplace.

Sentiment analysis for Indonesian regional languages faces two persistent challenges: labeled training data is extremely limited for most regional varieties, and transformer models pre-trained on Bahasa Indonesia do not generalize reliably to languages with substantially different morphological structures. Prior work on the NusaX benchmark has primarily relied on direct fine-tuning, treating each regional language independently and without exploiting linguistic proximity between related languages as a transfer signal. This paper proposes Language-Similarity-Guided Transfer (LSGT), a sequential fine-tuning strategy that first adapts a pre-trained model to a pivot language selected using character trigram similarity, followed by fine-tuning on the target language. Four transformer models are evaluated across all 12 NusaX languages using the official train/validation/test splits: IndoBERT, NusaBERT, mBERT, and XLM-R. Performance is evaluated using four metrics: accuracy, macro F1, macro precision, and macro recall. Experimental results show that LSGT improves macro F1 in 44 of 48 model-language combinations, demonstrating that the fine-tuning strategy itself is a major factor in low-resource cross-lingual sentiment classification. XLM-R benefits most strongly from LSGT, achieving an average improvement of +0.137 macro F1 and a peak gain of +0.298 on Madurese. SHAP-based token attribution analysis further reveals that predictions rely heavily on named entities and domain-specific nouns rather than sentiment-bearing vocabulary, indicating a dataset-level bias inherited from the original SmSA corpus and propagated through the NusaX translation pipeline.

Implementing REST in modern applications, security will be a key foundation for its development because the REST architecture requires communication between servers. In this study, we will enhance REST request security by using SHA-1 tokens and the Keccak algorithm. Tokens are the access keys for making requests. The token generation process is carried out on the server; the client will generate a token, and the server will return a valid token. This valid token can be used to request data from the server. Adding a token will impact the security and speed of REST. The token will be verified by the server and declared valid. If valid, the server will return the data; otherwise, the server will send an error message. Compared to using a token, data security is more assured. Furthermore, adding a token parameter will increase the token verification process, thus increasing the number of processes, which will impact speed. The results of this test show that server data security is better maintained and more secure compared to using a token, because anonymous users cannot access the data. The API access speed without a token is 48.8 milliseconds, while using a SHA-1 token is 62.3 milliseconds, and the Keccak algorithm is 58.9 milliseconds. The time efficiency reduction for implementing the SHA-1 token algorithm is 27.67% or 13.5 milliseconds, and the Keccak algorithm is 26.6% or 10 milliseconds.

The rapid growth of e-commerce in Indonesia, particularly the Shopee platform, has generated a large volume of user reviews on the Google Play Store, which can be analyzed to understand consumer sentiment. This study aims to compare the performance of the Support Vector Machine (SVM) and Random Forest (RF) algorithms in binary sentiment classification (positive and negative) on Shopee reviews, as well as to statistically test the significance of their differences using One-Way ANOVA. A total of 400,498 reviews were collected via web scraping, preprocessed through text normalization, tokenization, and Indonesian language stemming, and then feature-extracted using TF-IDF and Count Vectorizer. Evaluation results show that SVM achieved an accuracy of 91.77%, precision of 91.49%, recall of 91.77%, and F1-Score of 91.56%, while RF achieved an accuracy of 90.07%, precision of 91.68%, recall of 90.07%, and F1-Score of 90.55%. ANOVA confirmed that the performance difference between the two algorithms is statistically significant (p-value = 0.0007) with a large effect size (η² = 0.1815). Therefore, SVM is recommended as a more optimal and consistent algorithm for automated sentiment analysis of Indonesian e-commerce reviews, while also providing a replicable methodological framework for similar future research.

Budget efficiency is an important issue in state financial management because it is directly related to government spending priorities and their impact on public service programs. Discussions about budget efficiency policies are widespread on social media platform X, generating diverse public responses, thus necessitating an automated approach to understand public opinion trends more quickly and objectively. This research aims to analyze the sentiment of Indonesian people toward budget efficiency policies and compare the performance of the Naïve Bayes and Support Vector Machine (SVM) algorithms in classifying sentiment. The research data used 10,909 Indonesian-language tweets sourced from a public dataset, which were then processed thru the preprocessing stages including cleaning, case folding, normalization, tokenization, stopword removal, and stemming. Sentiment labeling is performed automatically using the Indonesian Sentiment Lexicon (InSet) approach to categorize data into positive, negative, and neutral sentiments. Feature extraction was performed using Term Frequency–Inverse Document Frequency (TF-IDF), and then the data was divided into training and testing sets with an 80:20 ratio. Model performance evaluation was conducted using a confusion matrix and the metrics of accuracy, precision, recall, and F1-score. The research results show that sentiment distribution is dominated by negative sentiment at 56.78%, followed by positive sentiment at 37.40%, and neutral sentiment at 5.83%. In the classification stage, SVM performed best with an accuracy of 86%, while Naïve Bayes achieved an accuracy of 74%. These findings indicate that SVM is more optimal for sentiment classification on social media text data and can be utilized to more effectively support the analysis of public response to budget efficiency policies.

The rapid growth of e-commerce platforms in Indonesia, particularly Tokopedia, has resulted in a large volume of consumer reviews containing valuable information regarding customer perceptions and satisfaction. However, manual analysis of such reviews is inefficient and prone to subjectivity, necessitating an automated approach based on machine learning. This study aims to classify the sentiment of sports product reviews on Tokopedia into positive, negative, and neutral categories by applying Logistic Regression, Support Vector Machine (SVM), and Random Forest using the Term Frequency–Inverse Document Frequency (TF-IDF) approach. The data were collected through web scraping of Indonesian-language sports product reviews and processed through several preprocessing stages, including data cleaning, case folding, tokenization, stopword removal, and stemming. Feature representation was performed using TF-IDF to transform textual data into numerical vectors, after which the dataset was divided into training and testing sets with an 80:20 ratio. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results indicate that the application of TF-IDF significantly improves the performance of all models, with SVM consistently achieving the most optimal performance compared to Logistic Regression and Random Forest. These findings demonstrate that classical machine learning algorithms combined with TF-IDF remain highly effective for sentiment analysis of Indonesian-language text. The implications of this study are expected to assist sellers in understanding customer opinions, support consumers in making informed purchasing decisions, and serve as a foundation for the development of sentiment analysis and recommendation systems on e-commerce platforms.

This study aims to examine the effect of the Time Token learning model on the speaking skills of fifth-grade students at SD Negeri Parung Bingung 1. The research employed a quantitative approach with a quasi-experimental design. The sample consisted of 58 students, divided into an experimental class (using the Time Token model) and a control class (using direct instruction). Data were collected through speaking skill tests (pre-test and post-test) and analyzed using descriptive and inferential statistical tests. The findings revealed a significant improvement in speaking skills in the experimental class compared to the control class. The average pre-test score of the experimental class increased from 23.67 to 35.03 in the post-test, while the control class improved from 31.07 to 40.11. An independent t-test indicated that the Time Token learning model had a significant effect on students’ speaking skills (p < 0.05). The study concludes that the Time Token model is effective in enhancing students’ speaking skills by providing equal opportunities for each student to speak, reducing anxiety, and promoting active participation in learning. Therefore, this model can serve as an alternative for teachers in developing more interactive and effective teaching methods.

This study aims to determine the influence of the Time Token Learning Type learning model combined with science literacy on communication skills and cognitive learning outcomes of SMPN XYZ students. The background of this research is low communication skills and student learning outcomes that are still substandard, so an innovative learning approach is needed that can improve both aspects. The research method used was quasi experimental with a Pretest-Posttest Control Group Design. The research subjects involved one experimental class given Time Token Learning type learning with science literacy content and one control class that used conventional learning. The research instrument consisted of a reasoned multiple-choice test to measure cognitive learning outcomes and an observation sheet to assess communication skills. The results of the study show that the application of the Time Token Learning model with science literacy has a significant influence on improving students' cognitive learning outcomes. The average pretest score of 40 increased to 75 in the posttest with an N-Gain value of 45.5% which was in the medium category. These findings prove that the learning model is effective in improving students' understanding of concepts and cognitive thinking skills. However, the results of the analysis of communication skills did not show a significant improvement. In addition, the correlation between communication skills and learning outcomes was also insignificant with a significance value of 0.826 > 0.05. In conclusion, the Time Token Learning model with science literacy has proven to be effective in improving students' cognitive learning outcomes, but has not been able to optimally develop communication skills. Therefore, it is necessary to develop additional strategies or a combination of other learning models so that communication skills can develop in line with improving cognitive learning outcomes.

This study aims to analyze the sentiment of customer reviews of the Grand Jatra Hotel Pekanbaru on the Google Review platform using the Naïve Bayes algorithm. Social media and online review platforms are increasingly becoming the primary source of information for potential customers in making purchasing decisions, particularly in the hospitality sector. Therefore, sentiment analysis of customer reviews is crucial for understanding consumer perceptions and providing strategic input for hotels in improving service quality. The research data was collected using web scraping techniques to obtain publicly available customer reviews. The obtained data was then processed through text preprocessing stages including case folding, tokenizing, normalization, stopword removal, and stemming. The Term Frequency-Inverse Document Frequency (TF-IDF) method was then used to weight each word, so that more relevant words have a greater influence in the classification process. The sentiment classification process was carried out into two main categories, namely positive and negative. The Naïve Bayes model was trained using training data and then tested with test data to measure the algorithm's performance in classifying sentiment. The evaluation results show that the model built is able to achieve an accuracy level of 98%, with a precision value of 97% and a recall of 100% in the positive class, and 92% in the negative class. These findings confirm that the Naïve Bayes algorithm can be effectively used in analyzing customer sentiment towards hotel services and facilities. Practically, the results of this study are expected to provide insight for the management of Grand Jatra Hotel Pekanbaru in understanding customer perceptions, identifying service strengths and weaknesses, and formulating more targeted marketing strategies. In addition, this study can also be a reference for the development of similar studies in the hotel industry and other service sectors.

This research is motivated by the low enthusiasm, participation, and creativity of students in social studies learning which is considered boring and difficult, resulting in low learning outcomes. One effort to overcome this problem is to apply the Project Based Learning (PjBL) learning model based on the Mirigambar Temple photography project through Blogger media. This study aims to determine the effect of PjBL on learning outcomes, creativity, and both simultaneously. The study used a quantitative approach with a quasi experimental nonequivalent control group design. The sample consisted of 20 control class students and 20 experimental class students selected using the purposive sampling technique. The instruments used were creativity questionnaires and learning outcome tests. Data analysis used the Independent Sample T-Test and MANOVA. The results showed that PjBL learning had a significant effect on learning outcomes, creativity, and learning outcomes and creativity of students together. These findings indicate that the application of PjBL through a Blogger-based photography project can create active, enjoyable learning, and is able to optimally increase student potential, so it is worthy of being an alternative strategy for learning social studies in schools.

This study presents an advanced AI-powered framework to detect and prevent cyberbullying across diverse social media platforms using a multiclass classification approach. Addressing the growing complexity and linguistic diversity of online abuse, the research integrates various machine learning (RF, LR, SVM) and deep learning (Bi-LSTM, BERT) models trained on a balanced dataset covering bullying categories based on religion, age, ethnicity, gender, and neutral content. Data preprocessing, tokenization, feature extraction via TF-IDF and CountVectorizer, and class balancing using SMOTE were applied to enhance model accuracy. The proposed system further supports real-time detection through social media APIs, offering dynamic monitoring and intervention capabilities. Among the tested models, Random Forest and BERT achieved the highest classification performance with 94% accuracy. Despite its robust architecture, limitations include dependence on English-language datasets, exclusion of multimodal data (e.g., memes, audio), and API restrictions that challenge scalability. Future development will focus on incorporating vision-language models and optimizing the system for real-time, multilingual, and multimodal environments. This study contributes to digital safety efforts by proposing a scalable and adaptive detection system suitable for safeguarding users from evolving forms of online harassment.

This research aims to analyze. (1) The influence of learning models on student learning outcomes. (2) The influence of social studies learning outcomes on students who have high interest and students who have low interest. (3) The interaction between the learning model and the level of interest influences student learning outcomes. This research is a quasi-experimental research (quasi-experiment). This population is class V students at SD Negeri 106827 Desa Durian. The sample in this study was selected using purposive random sampling from two classes. The experimental class was treated with the time token model, the control class was treated with the Talking Stick model. The instruments used consisted of: learning results tests and learning interest questionnaire sheets. Data analysis was carried out using two-way ANOVA.  The results of this research indicate that the time token learning model is a solution and alternative for teachers to improve students' social studies learning outcomes.  

Named Entity Recognition (NER) is a crucial natural language processing task that extracts and classifies named entities from unstructured text into predefined categories. While existing NER methods have shown success in general domains, they often face significant challenges when applied to specialized contexts like Filipino cultural and historical texts. These challenges stem from the unique linguistic features, and diverse naming conventions. This research introduces an enhanced rule-based NER approach that specifically addresses these challenges. At its core, the system utilizes curated Corpus of Historical Filipino and Philippine English (COHFIE), which serves as both training and evaluation data. This research presents an enhanced rule-based approach for NER using a Corpus of Historical Filipino and Philippine English (COHFIE) building on pattern-learning methods, incorporating character and token features, and by using positive and negative example sets. To enrich the classification process, we used the International Committee for Documentation – Conceptual Reference Model (CIDOC-CRM), a cultural heritage framework, to provide a more nuanced categorization of entities based on their historical and cultural significance. Tested across existing Filipino based models (calamanCy and RoBERTa Tagalog), the enhanced model shows improvement on identifying entities related to Filipino culture (CUL) and history terms (PER, ORG, LOC).

This study aims to analyze the sentiment of iPhone product reviews fromAmazon using the BERT (Bidirectional Encoder Representations from Transformers) model to classify reviews as either positive or negative. The dataset, sourced from Kaggle, includes text reviews and star ratings, where high ratings indicate positive sentiment and low ratings indicate negative sentiment. After text preprocessing steps, including data cleaning, tokenization, and sentiment labeling, the BERT model was fine-tuned for sentiment classification, with the data split into training, validation, and test sets. Evaluation results demonstrate that the BERT model achieves a high classification accuracy, with an accuracy rate of 93.9% and a balanced F1 score between precision and recall. Confusion matrix evaluation also indicates that the model consistently identifies both positive and negative sentiments. This study shows that Transformer-based models like BERT are highly effective in understanding customer opinions in e-commerce, with broad application potential for data-driven decision-making in marketing strategies and product development.

A Thesis English Education Department the Faculty of Teachers Training and Education, stkip us Kutacane.The aim of the research was to find out The Effectiveness of Using Time Token (TT) Model To Improve Student Speaking Skills at VII grade MTs Swasta Nurul Islam Academic Year 2023-2024. The population of this study consists of all 25 students in Class VII, with a sample size of 25 students. The research method employed is an experimental method with a one-group pretest and posttest design, and data analysis using the "t" test. The initial test results show that students had an average score of 46.8, categorized as less satisfactory, with a standard deviation of 6.14. There was an improvement in the final test scores, with an average score of 78.28, categorized as good, and a standard deviation of 5.41. Based on the initial and final test results, and considering the passing grade (KKM) for English in high school is 70, Improve Student Speaking Skills is classified as good. The hypothesis testing yields a t-value of 17.20, compared with the t-table value at a 5% significance level (1.711). As a result, the hypothesis is accepted (17,20> 1.711)In conclusion, there The Effectiveness of Using Time Token (TT) Model To Improve Student Speaking Skills at VII grade MTs Swasta Nurul Islam Academic Year 2023-2024.

The rapid development of information and communication technology allows society to access various information needed in daily life. The Law of the Republic of Indonesia Number 23 of 2006 concerning population administration serves as an important element in population management. Population documents are issued by official institutions and have legal legitimacy as valid evidence. The method used in this research regarding public sentiment towards e-ID card services is the survey method, which aims to collect data from a large population using a smaller sample. The steps or processes in this research using the SVM method consist of case folding, cleaning, tokenizing, normalization, stopword removal, and stemming. Based on the classification of 150 test data using SVM, the number of positive sentiments recorded is 110 opinions, while negative sentiments recorded are 40 opinions.

This research aims to address the issue of uneven bandwidth distribution in large organizational networks by implementing Quality of Service (QoS) using FIFO and the Hierarchical Token Bucket (HTB) algorithm on Mikrotik routers. Uneven bandwidth distribution can disrupt productivity and operational efficiency. This study creates a fair and efficient traffic management system, allowing bandwidth allocation according to user needs. The methodology involves detailed configuration of Mikrotik RouterOS to optimize QoS with adjusted HTB settings. Testing was conducted using IPerf3 to measure bandwidth variations received by clients in different conditions, including scenarios with two and three active clients. The results indicate that the HTB method provides more stable and consistent bandwidth distribution compared to FIFO. In the two-active client scenario, the unused bandwidth by the third client is allocated to higher priority clients, demonstrating HTB's effectiveness in managing traffic priorities. This research is expected to enhance user satisfaction by providing a network that is both stable and responsive to the needs of various operational applications, and contribute significantly to the development of best practices for bandwidth management in complex organizational environments.