Publication Search

User reviews on the Shopee e-commerce platform represent an important source of information for understanding consumer perceptions of products and services. Sentiment analysis is commonly applied to classify user opinions into positive, neutral, and negative sentiment categories based on textual data. This study aims to analyze the performance of the Long Short-Term Memory (LSTM) method in sentiment classification of Shopee user reviews. The dataset used in this study consists of Indonesian-language user reviews that have undergone preprocessing stages, including case folding, text cleaning, tokenization, and stopword removal. The LSTM model was trained using preprocessed text represented as word sequences. Model performance was evaluated using overall accuracy and class-wise classification results. The experimental results indicate that the LSTM method achieved an overall accuracy of 87.62%. In addition, the classification performance for the positive sentiment class reached 95.27%, the neutral class achieved 4.96%, and the negative class reached 74.26%. These results demonstrate that the LSTM method performs well in classifying sentiment in Shopee user reviews, particularly for positive sentiment. This study is expected to provide insights and references for the application of deep learning methods in sentiment analysis of Indonesian e-commerce review data.

This paper explores the epistemological dimensions of the digital transformation occurring in traditional game development through the integration of machine learning systems. By examining how knowledge creation, validation, and application have evolved in this domain, we identify fundamental shifts in the epistemological frameworks governing game development practices. The research investigates how machine learning has redefined creative processes, technical implementation, and experiential design while challenging traditional notions of authorship, expertise, and knowledge transmission. Through analysis of industry case studies, technological capabilities, and theoretical frameworks, this paper contributes to understanding how machine learning systems are not merely tools but epistemological agents that fundamentally transform how knowledge is generated, validated, and utilized in game development ecosystems.

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.

Indonesian Sign Language (BISINDO) serves as a primary communication medium for the deaf community; however, limited public understanding often creates barriers during daily interactions. This study aims to develop a real-time BISINDO word-level translation system using hand landmark extraction and temporal modeling with Long Short-Term Memory (LSTM). The system employs MediaPipe Hands to detect 21 hand landmarks per frame, which are then processed as sequential motion patterns to classify five BISINDO words: saya, terima kasih, maaf, nama, and kamu. A total of 250 gesture samples were recorded under controlled lighting conditions as the primary dataset. The processed sequences were used to train the LSTM model, which was subsequently integrated with an ESP32 microcontroller and a DFPlayer Mini module to produce direct audio output. Experimental results show that the model achieved an average accuracy of 86%, with precision and recall values ranging from 0.81 to 0.94. The confusion matrix analysis indicates that most gestures were correctly classified, although some errors occurred in gestures with similar initial motion trajectories. Integration testing demonstrated an average system latency of 3.8 seconds and an audio output success rate of 85%. These findings indicate that the proposed system is capable of translating BISINDO word-level gestures accurately, responsively, and consistently in real-time conditions. This study provides a strong foundation for the broader development of sign language translation systems, with potential enhancements in vocabulary expansion, multi-user datasets, and hardware optimization for deployment in real-world environments.

Drug abuse (Narcotics, Psychotropics, and other Addictive Substances) is a serious problem that can threaten the younger generation, especially in the Panggung Kidul Village area. The lack of public understanding, especially teenagers, regarding the dangers and negative impacts of drug abuse is one of the factors that influence the high risk of substance abuse. Therefore, innovative and interactive educational media are needed to increase public awareness and understanding regarding the prevention of drug abuse. This study offers a solution by designing and developing educational media based on Augmented Reality (AR) technology as a visual and interactive tool that conveys information in an interesting and easy-to-understand manner. The use of smartphones as the main device in AR applications makes this media more easily accessible to various groups of people. The test results using the System Usability Scale (SUS) method showed a user satisfaction level of 96% which is included in the Acceptable category. Thus, this AR-based educational media is expected to be an effective means of increasing public understanding of the dangers of drug abuse and encouraging early preventive efforts.

Technological advancements have brought fundamental changes in the way we interact with digital images and photography. One significant milestone in this development is the Photoshop Express Photo Editor, which has become a primary platform for image processing and editing. Datasets are used to analyze sentiment and are utilized during the accuracy testing phase. Based on the testing results, the Convolutional Neural Network (CNN) algorithm achieved an average accuracy value of 86.50%, compared to the Naïve Bayes (NB) algorithm, which achieved an average accuracy value of 75%. The results of the research conclude that the choice of sentiment analysis method should be tailored to the needs and limitations of the system. If a fast, light, and easy-to-understand process is required, the Naive Bayes method is the right choice. However, if accuracy and context understanding are the top priorities, then CNN is a superior approach, although it requires more resources. Additionally, based on the Wordcloud data, it is known that the majority of comments are positive, indicating that the reviews or texts analyzed contain many positive expressions related to quality, usability, and ease of use.

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.

This study focuses on creating a Turnitin tutorial application to track plagiarism using the prototype method approach. The purpose of this application is to make it easier for users to understand and utilize Turnitin as a reliable plagiarism detection tool in academic writing. The prototype method was chosen because it allows for rapid iteration and improvement based on user feedback, which is very important to improve the quality of the application. The development stages include creating an initial prototype, testing functions, and collecting feedback for design refinement. This study aims for the application to be developed to provide clear guidance and effective solutions in identifying and preventing plagiarism, while deepening users' understanding of the use of Turnitin. Thus, this application is expected to strengthen academic integrity and support ethical writing practices through integrated plagiarism detection technology.

Based on the observations that have been made at the Arri’ayah Islamic Boarding School in Lembak Village, Lembak District,Muara Enim Regency, the problems found are. Teaching and learning activities that are less interactive, in learning the law of tajwid in hidayatus sibyan’s book, students are still difficlut to understandt the material and there needs to be other alternatives to help students understand the materia being studied, one alternative is the use of technology for education, namely by using learning media. Especially now that may students are not interested in learning to use books, they reason that learning to use book is boring which ultimately impacts on students’ lack of understanding of the material that has been presend, tharefore that researcher designed learning media for the law of tajwid hidayatus sibyan, so that students are more interested when study, in collecting data researchers used descriptive qualitativ methods including conducting interviews, direct observation, and literature study and are built using UML (Unifield Modelling Language).

Learning Media applications that use an Android-based material delivery system are expected to facilitate the delivery of material, where previously material was only found in books and the internet. Learning materials that only come from books reduce the reader's understanding because there are only text and pictures. This is what underlies the selection of the thesis title "Application of Android-Based Hydroponic Vegetable Growing Learning Media Application" in the hope that it can be a solution to help people who take part in the training understand material about growing vegetables by hydroponics.Hydroponics is an agricultural activity carried out by using water as a medium to replace soil. So, hydroponics can be interpreted as a work or management of water as a medium for plant growth without using soil media as a planting medium and taking the required mineral nutrients from a nutrient solution dissolved in water. The learning media application for growing hydroponic vegetables based on Android is limited to material on hydroponics, planting media and tools used in hydroponics, the steps needed for hydroponic farming, systems or techniques that exist in hydroponics.

In the current era, learning adheres to the 2013 curriculum which includes HOTS (Higher Order Thinking Skills) consisting of critical thinking competencies, creativity and innovation, communication skills, collaboration skills and selfconfidence. These five things need to be trained or improved for deaf children so that they can take part in learning well. So learning media products are made that can be used to recognize letters and numbers. This Learning Media is equipped with sign language to support the understanding of deaf children in addition, it is packaged with an attractive appearance so that deaf children are interested in learning it. Often in daily teaching and learning activities students still often experience problems in remembering the material being taught both in the introduction of letters and also the introduction of numbers and what becomes an obstacle for students learning must be done repeatedly so that they can remember it and can really understand what it means. being taught and also they are sometimes bored and lazy in learning. From the problems that occur above, it is necessary to have a learning media that can help children with disabilities, especially the deaf, especially for the introduction of numbers and letters so that they can easily understand and understand letters and numbers. not bored, bored and lazy in learning. Learning media in the form of an android application so that it can be used on smartphones which are currently very widely used by both teachers and parents of students with disabilities.

At this time the learning process is still partially carried out online (in the network) considering the positive cases of Covid-19 that still exist in the Semarang City area. The implementation of online learning is not without problems, even in several countries, especially Indonesia, it is reported that countries that adopt online learning on average are actually much smaller than expected. The implementation of online learning makes students less understanding of the learning materials provided and students' low interest in learning during the pandemic. This study aims to create a learning application for grade VI elementary school students that contains learning materials, practice questions that are randomized using LCM and facilitate the results of the assessment of the questions. From the results of LCM randomization, each student did not get the same or twin questions. From the test of 3 students, it was found that the questions that appeared in the same order were question number 6, while the questions that appeared in a different order were questions number 2, 3, 4, 5, 7, 8, 9, 10

Virtual teachers are devices or agents with the function of replacing the role of humans (teachers) with their teaching skills. The virtual teacher also has a function as task facilitator and is presented during training, especially when the teacher is actually not present. The virtual teacher's objectivity is carried out by explaining the subject matter in a virtual environment, for example, virtual independent learning. In the western world, virtual schools are quite widely applied, especially to students who are homeschooling. In a virtual school, all materials, assignments and grades are accessed via the internet. The virtual teacher concept refers to a device that provides guidance and practice. Teachers who are equipped with interactive agent functions that can provide direction and feedback in order to improve student abilities. By utilizing natural language processing (NLP) and pattern matching to help students learn alone without being accompanied by a teacher. NLP is used as a learning tool as outlined in the text of the sentence as part of the learning material which is done virtually. Meanwhile, pattern matching is used to group the questions asked so that the computer can gain an understanding of the questions posed by students. This grouping aims to solve problems with different word order which basically have different meanings. The teacher has the facility to make material, make questions, and answer student questions. A teacher can add knowledge about the database to enrich the source of knowledge for students.

Based on the results of observation, the learning method used in SMP Muhammadiyah 3 Kaliwungu is in the form of discourse, discussions, question and answer with the book media. Learning methods that have been applied so far have not had enough impact on students' level of understanding. The method used is less successful, so students feel bored and bored. This study offers a solution for multimedia utilization with the Mind Map method as an interesting learning media, where computers can display text, images, videos and audio so that students can have a pleasant impression in the learning process. The validity value of media experts is 2.9 which is declared feasible, while the validity value of material experts is 3.3, which is declared feasible, and increases students' understanding and interest as users from 58.5% up to 80.5%.

Utilization of a mobile device with the Android operating system that is used as a supporting medium and supplement in improving learning outcomes combined with demonstration and discovery learning or demon-disco learning methods is needed to help students improve learning outcomes in vocational competence subjects in hydroponic crop cultivation in vocational high schools Kristen Terang Bangsa, because the use of android-based applications can provide new experiences regarding the use of information and communication technology, as well as provide opportunities for students to be able to learn more independently. The concept chosen as a learning media is to explain the material about understanding, introduction of parts, types, and quiz containing questions about hydroponic plant cultivation. This research uses the Research and Development (RnD) product development method, using 6 out of 10 stages research that is the potential and problems, data collection, product design, design validation, design improvement, product trials. The results of this study are to produce learning media in the form of Android-based applications. The validity value of media experts is 2.6 which is declared feasible, while the validity value of material experts is 3.6 which is declared feasible, and is able to increase the average value in the subject of vocational competence in hydroponic cultivation in Christian Terang Bangsa Vocational Schools which initially 67 (with 13 students who had not yet reached KKM) to 80 (with 4 students who had not yet reached KKM).