Publication Search

Big data is a collection of data that has a large volume, so traditional data processing technology is unable to handle it well. Marketplace is a platform that most people often use to shop online. On this platform there is a comments column for writing reviews of products that have been purchased. Consumer reviews have an important role in understanding customer perceptions and sentiments towards the products being sold. Classification uses the Support Vector Machine method. The goal is to classify consumer reviews into positive or negative sentiment categories. The test uses data from more than 300 data samples with the assumption of independence between the features in the data. The results of big data analysis of consumer sentiment reviews of health masks on the marketplace used the support vector machine method with an accuracy value of 88%. The results of the analysis can be concluded that the dominant results of scraping reviews on health mask products lead more to positive reviews. The results on wordcloud of negative reviews provide insight to improve the quality of masks which are still lacking in terms of thinness, straps breaking easily, tears, holes, rubber quality and product packaging.    

This study explores the role of sentiment analysis as a predictive tool for understanding and forecasting product launch success in the digital market. Sentiment analysis involves the classification of consumer sentiment expressed on social media platforms such as Twitter and Instagram, and it can significantly impact businesses by predicting consumer behavior and product performance. The research highlights the relationship between social media sentiment and product success, demonstrating that positive sentiment is strongly correlated with higher sales and consumer engagement, while negative sentiment can lead to declines. Machine learning models, including Support Vector Machines (SVM) and Random Forest, were employed to classify sentiment from large volumes of social media data and correlate it with product performance indicators such as sales volume and consumer interaction. The study found that sentiment analysis models were highly effective in predicting product success, with positive sentiment generally driving product profitability and negative sentiment posing a potential threat to brand reputation. Moreover, the analysis showed that social media sentiment provides real-time insights into consumer perceptions, enabling businesses to quickly adjust marketing strategies and product development plans. These findings underscore the importance of integrating sentiment analysis into product launch evaluations and strategic decision-making. Future research should explore the integration of sentiment analysis with other predictive market models and investigate the effects of fake reviews and post-purchase consumer behaviors on product success.

This research uses the Support Vector Machine (SVM) algorithm to predict Persebaya Surabaya's ranking in BRI Liga 1. The data used includes goals scored, goals given away, total end-of-season points, and status as champions. The results of the analysis using Orange software show that Persebaya Surabaya does not necessarily become a champion if it has a point value of 42 and an SVM value of 41. To become a champion, Persebaya Surabaya must score 69 points or more in a season and achieve an average of more than 54 goals per season. The suggestion of this research is to have more data so that the results of data processing using Orange software are more optimal and accuracy is more precise.

Brain tumors are abnormal cell growths in brain tissue that can be life-threatening. This study aims to classify brain tumors to help early diagnosis. The method used is to extract features from brain MRI images using Local Binary Pattern (LBP) and then classified with Support Vector Machine (SVM). The data used were 2044 brain MRI images consisting of 3 classes namely meningioma, no tumor, and pituitary. The best results were obtained using LBP with a radius of 1 and the number of neighbors 8, while the best SVM model used the RBF kernel with a C value of 50, resulting in 88% accuracy, 86% precision, and 87% recall. It can be concluded that the combination of LBP and SVM methods is effective enough to classify brain tumor types to support early diagnosis.

Chronic Kidney Disease (CKD) is a serious health problem, with significant impact on patients' quality of life and healthcare costs. In an effort to improve early diagnosis, a comparison was made between several Machine Learning algorithms used for analysis of patient clinical data. This clinical data contains the medical history or health records of patients. The Machine Learning algorithms used in this study include K Nearest Neighbor (KNN), Support Vector Machine (SVM), and Logistic Regression. By searching for the best algorithm through the calculation of Accuracy, Precision, and Recall with comparasion when using SMOTE (Synthetic Minority Oversampling) to balancing the class attribute.   

This study aims to analyze the communication of marine mammals, especially whales and dolphins, through a bioacoustic approach combined with computational science as an effort to support conservation in the Tropical Ocean region. The focus of the location is on the Banda Sea, the Seram Sea, and the tropical Pacific region which are important migration routes for marine mammals. Data were obtained from underwater sound recordings using hydrophones, accompanied by visual observations to validate the behavior and existence of species. The analysis is carried out through several stages, including signal pre-processing with noise filtering and sound segmentation, spectral analysis using Fast Fourier Transform (FFT), as well as the creation of a spectrogram to visualize vocalization patterns. Machine learning algorithms such as Support Vector Machine (SVM) are used to classify interspecies voices, while deep learning approaches are applied to identify more complex communication patterns, including dialect variations. The results showed that whales produced low-frequency vocalizations (20–200 Hz) for long-distance communication, while dolphins used high-frequency clicks and whistles (5–20 kHz) for echolocation and social interaction. The integration of bioacoustics and artificial intelligence improves the accuracy of sound classification by more than 90%. These findings confirm the effectiveness of computational-based non-invasive methods in monitoring the presence and behavior of marine mammals and provide a scientific basis for sustainable conservation.

PeduliLindungi is an application from the Government of Indonesia that was made in response to the COVID-19 pandemic. Since its initial release in 2020, this application has received many updates with the goal of improving its overall performance. One of the basics of updating applications is to process the reviews given by users at the Google Play Store using sentiment analysis. The methods used this time are Naive Bayes Classifier (NBC) and Support Vector Machine (SVM). The sample data used were 300 reviews with positive feedback and 300 reviews with negative feedback, for a total of 600 user reviews. The results of the NBC algorithm calculations produce an accuracy of 76%, a precision of 76%, a recall of 82%, and an f1-score of 79%. As for the SVM algorithm, it produces an accuracy rate of 80%, a precision of 83%, a recall of 80%, and an f1-score of 81%.

Organisasi Kesehatan Dunia (WHO) secara resmi menyebut virus Covid-19 sebagai pandemi global, oleh karena itu semua negara di dunia berusaha meminimalkan dampak yang ditimbulkan oleh virus tersebut, yaitu dengan mengembangkan vaksin. Dalam konteks pandemi Covid-19, pemerintah Indonesia juga meminta dan mendorong masyarakat untuk turut serta mendukung vaksinasi, namun upaya tersebut sebenarnya memiliki kelebihan dan kekurangan, sehingga banyak masyarakat yang mengutarakan pendapatnya di jejaring sosial salah satunya Twitter. Penelitian ini bertujuan untuk mengetahui hasil penerapan analisis sentimen dan mengukur performansi algoritma Naïve Bayes Classifier (NBC) dan Support Vector Machine (SVM) terhadap data vaksin Covid-19 dengan cara mengklasifikasikan data tersebut ke dalam kelas positif dan negatif. Data tweet yang didapat kemudian dilakukan text preprocessing untuk mengoptimalkan pengolahan data. Terdapat 4 tahapan text preprocessing antara lain Case Folding, Tokenizing, Filtering, dan Stemming. Penelitian ini mengkaji kinerja Naïve Bayes Classifier (NBC) dan Support Vector Machine (SVM) dengan menambahkan teknik TF-IDF (Term Frequency-Inverse Document Frequency) yang bertujuan untuk memberikan bobot pada hubungan kata (term) sebuah dokumen. Kemudian melakukan splitting data yaitu membagi data training 80% dan data testing 20% dengan harapan mendapatkan model dengan performansi terbaik dan yang terakhir melakukan visualisasi data tweet dengan menggunakan Word Cloud agar bisa menarik sebuah kesimpulan. Hasil klasifikasi data tweet vaksin Covid-19 menggunakan algoritma Naïve Bayes Classifier mendapatkan nilai accuracy sebesar 81%, precision sebesar 80%, recall sebesar 99%, dan f1-score sebesar 89%, Sedangkan untuk algoritma Support Vector Machine mendapatkan nilai accuracy sebesar 87%, precision sebesar 88%, recall sebesar 96%, dan f1-score sebesar 92%.

Penyakit hipertensi merupakan manifestasi gangguan keseimbangan hemodinamik sistem kardiovaskular yang mana patofsiologinya multifaktor yang cukup banyak mengganggu kesehatan masyarakat. Pada umumnya pasien tidak mengetahui bahwa menderita penyakit hipertensi sebelum memeriksakan tekanan darahnya, ini menyebabkan hipertensi merupakan suatu penyakit kronis yang disebut dengan silent killer. Salah satu yang dapat membantu dalam proses penegakkan diagnosa hipertensi dengan mengembangkan sebuah Rancangan Sistem Pakar Penegakan Diagnosa Penyakit Hipertensi, dalam penelitian ini menggunakan metode penelitian Inferensi Forward Chaining, Metode Support Vector Machine (SVM). Data yang digunakan yaitu data primer dan sekunder. Tujuan dari penelitian ini memudahkan tenaga medis dan penderita dalam mengetahui gejala awal penegakan diagnosa hipertensi, agar segera bisa dilakukan penangan yang cepat dan akurat. Hasil dari penelitian model SVM linear terhadap 247 data pasien menunjukkan akurasi 85% pada proses training dan 91,89 % pada proses testing.  

Plants are constantly exposure to pathogens such as virus, bacteria and fungi. Plant diseases caused by pathogens lead significant crop yield loss globally. Numerous researchers have been studying how to reduce the damage of plant diseases. Plant disease has long been one of the major threats to agriculture security in India because it dramatically reduces the crop yield and compromises its quality. Pests and Diseases results in the destruction of crops or part of the plant resulting in decreased food production leading to food insecurity. Accurate and precise diagnosis of diseases has been a significant challenge. Traditionally, identification of plant diseases has relied on human annotation by visual inspection. Plant diseases affect the growth of their respective species; therefore their early identification is very important. Modern technological approaches such as machine learning and deep learning algorithm have been employed to increase the recognition rate and the accuracy of the results. Various researches have taken place under the field of machine learning for plant disease detection and diagnosis, such traditional machine learning approach being random forest, artificial neural network, support vector machine(SVM), fuzzy logic, K-means method, Convolutional neural networks etc. In this paper a comparative study on machine learning techniques for plant disease detection is performed. In this survey it observed that Convolutional Neural Network gives high accuracy and detects more number of diseases of multiple crops.

Plants are constantly exposure to pathogens such as virus, bacteria and fungi. Plant diseases caused by pathogens lead significant crop yield loss globally. Numerous researchers have been studying how to reduce the damage of plant diseases. Plant disease has long been one of the major threats to agriculture security in India because it dramatically reduces the crop yield and compromises its quality. Pests and Diseases results in the destruction of crops or part of the plant resulting in decreased food production leading to food insecurity. Accurate and precise diagnosis of diseases has been a significant challenge. Traditionally, identification of plant diseases has relied on human annotation by visual inspection. Plant diseases affect the growth of their respective species; therefore their early identification is very important. Modern technological approaches such as machine learning and deep learning algorithm have been employed to increase the recognition rate and the accuracy of the results. Various researches have taken place under the field of machine learning for plant disease detection and diagnosis, such traditional machine learning approach being random forest, artificial neural network, support vector machine(SVM), fuzzy logic, K-means method, Convolutional neural networks etc. In this paper a comparative study on machine learning techniques for plant disease detection is performed. In this survey it observed that Convolutional Neural Network gives high accuracy and detects more number of diseases of multiple crops.

Kontaminasi bakteri patogen dalam produk makanan mahal bagi masyarakat dan industri. Metode tradisional untuk mendeteksi dan mengidentifikasi patogen bawaan makanan seperti Listeria monocytogenes biasanya memakan waktu 3-7 hari. Pada makalah ini, sistem klasifikasi dikembangkan untuk mengidentifikasi pengambilan citra bakteri menggunakan alat optical light scattering dan menghasilkan citra berbentuk grayscale. Algoritma klasifikasi yang diusulkan didasarkan pada Invariant Zernike Moment berbasis Support Vector Machine pada kernel Radial Chebyshev Moments yang dihitung dari dataset citra bakteri apda 4 genus yang digunakan sebagai dataset. Sebanyak 400 citra bakteri dengan 100 citra pada masing-masing jenis genus telah di uji dan menghasilkan akurasi pada proses indetifikasi dengan capaian sebesar 78,33% pada 5-fold Cross Validation.

With the increasing development of technology the more variety of books circulating on the internet. As is the recommendation system on online book sites that provide books relevantly and as needed with one's preferences. One alternative is GoodReads, a social networking site that specializes in cataloging books and users can share reading book recommendations with each other by rating, reviewing, and commenting. As a large book recommendation site, it has a lot of data that can be processed by applying machine learning methods, but still not known as the most accurate model. By using the right model, we can provide more accurate recommendations. Therefore, this study will analyze the data obtained from the www.kaggle.com namely the goodreads-books dataset. This study proposed a data mining classification model to get the best model in recommending books on GoodReads. The algorithms used are Decision Tree, K-Nearest Neighbor, Naïve Bayes, Random Forest, and Support Vector Classifier, then for model evaluation using accuracy, precision, recall, f1-score, confusion matrix, AUC, and Mean Error Absolute. The test results of several classification algorithms found that Decision Tree has the highest accuracy among the methods presented by 99.95%, precision by 100%, recall by 96%, f1-score of 98% with MAE of 0.05 and AUC of 99.96%. This is proof that decision tree algorithms can be used as book recommendations based on book categories on GoodReads.

Abstract In this study that was used as the object of research in classifying red wine based on the quality influenced by each red wine or red wine based on the content of each type of wine, from each attribute containing the composition in the wine seen which attributes most affect the quality of red wine, so that it will be known ingridents that can improve the quality of the wine, in this study was carried out by the application of Machine learning by comparing three algorithms of mining data that is , Decission Tree, Random Forest and Support Vector Machine (SVM), from the results of research that has been done by comparing the three algorithms, Random Forest produced the best accuracy among other algorithms that have been tested. Random Forest with accuracy results of 0.7468 makes this algorithm best used to classify the quality of red wine. And in the second order Decission Tree with accuracy results of 0.7031, while Support Vector Machine (SVM) get an accuracy result of 0.65. So in the research that has been done to classify the quality of red wine based on its composition Random Forest becomes the best algorithm to use..