Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika

PREDIKSI HARGA BERAS PREMIUM TAHUN 2024 MENGGUNAKAN METODE GRADIENT BOOSTED TREES REGRESSION

2024-08-15T14:37:16+00:00

Food needs are a special concern among the community. Every year the growth of Indonesian society increases so that the amount of food needed increases, especially rice which is the staple food of Indonesian society. Regarding this, the public needs information regarding forecasting rice prices for future needs. Therefore, this research aims to predict rice prices using the Gradient Boosted Trees Regression method. This method was chosen because of its ability to produce accurate predictions by minimizing errors through an ensemble approach. Evaluation is seen from the R-Squared and Root Mean Square Error (RMSE) values. The results of research using the Gradient Booster Trees Regression model obtained an R-Squared value of 0.9047 and an RMSE value of 0.0473, which indicates that the model has a high level of accuracy in predicting rice prices. The results of the dataset testing are divided into 80 percent training data and 20 percent for testing data. Based on this research, model testing was carried out by displaying decision tree visualization, using a sample of 50 decision trees.

ANALISIS PENYAKIT PADA TUMBUHAN HIDROPONIK SELADA MENGGUNAKAN METODE FORWARD CHAINING

2024-08-15T14:41:14+00:00

This research, titled "Analysis of Diseases in Hydroponic Lettuce Plants Using the Forward Chaining Method," focuses on the process of identifying diseases in hydroponic lettuce plants through an expert system. Hydroponic lettuce plants can be affected by various diseases such as soft root, root rot, yellowing leaves, and others. Therefore, there is a need to facilitate farmers and laypeople in detecting diseases in hydroponic lettuce plants and easily identifying them by simply answering diagnostic questions about the disease symptoms. This research develops the results of the disease analysis in hydroponic lettuce plants using the Forward Chaining method through an expert system. The Forward Chaining method is used due to its high effectiveness and accuracy in identifying diseases through IF-THEN Rule s by finding facts from the established Rule s. The data presented includes disease data and symptom data obtained from hydroponic lettuce cultivation on Jalan Muang RT 47 Lempake. This research involves data collection, data analysis, and BlackBox testing. The development of the website for analyzing diseases in hydroponic lettuce plants using the Forward Chaining method employs PHP, HTML, CSS, and MySQL programming languages. The results of this research are satisfactory because the Forward Chaining method can accurately detect diseases, and the website runs smoothly and also got an accuracy of 79,16% on the calculation system using the website.

ANALISIS SENTIMEN PADA ULASAN APLIKASI GOOGLE MAPS TERHADAP PELAYANAN BADAN PENYELENGGARA JAMINAN SOSIAL (BPJS) KESEHATAN SAMARINDA MENGGUNAKAN METODE K-NEAREST NEIGHBOR DENGAN FITUR EKSTRAKSI TF-IDF

2024-08-15T14:42:09+00:00

This study aims to analyze public sentiment towards the services of BPJS Kesehatan Samarinda based on reviews on the Google Maps application. The method used in this research is K-Nearest Neighbor (KNN) with TF-IDF (Term Frequency-Inverse Document Frequency) feature extraction. The data used consists of 500 Indonesian-language reviews collected through web scraping techniques. After the data collection process, the data was labeled by an expert, and then a pre-processing stage was carried out, including case folding, cleaning, tokenizing, stop word removal, and stemming. The data was then weighted using the TF-IDF method to identify important words. The testing was conducted using a training and testing data ratio of 70:30 and a k value of 5. The results showed that the KNN method was able to classify positive and negative sentiments with an accuracy rate of 93.3%. This analysis provides an overview of the service quality of BPJS Kesehatan in Samarinda and can be used as a basis for service improvements. Additionally, this research contributes to the use of KNN and TF-IDF for sentiment analysis, opening opportunities for further research in this field.

IMPLEMENTASI METODE DOUBLE EXPONENTIAL SMOOTHING HOLT PADA PERAMALAN IPM DI KALIMANTAN TIMUR

2024-07-11T00:43:56+00:00

Human Development Index (HDI) is a human development measuring tool introduced by the UNDP in 1990. Based on data from the East Kalimantan Central Statistics Agency (BPS), since 2010, the East Kalimantan Province HDI has experienced an upward trend with a decline in 2020 due to pandemic . In 2022, East Kalimantan Central Statistics Agency recorded the HDI value for East Kalimantan as reaching 77.44. This achievement makes East Kalimantan Province a province with a high level of human development and the 3rd ranked province with the highest HDI nationally. Based on this ranking, there is still room for the government to increase the HDI value of East Kalimantan to prepare it to become the new capital of the country. Therefore, a forecast is needed to find out the HDI value of East Kalimantan Province for the next few years as a consideration for the government in making policies. One forecasting method that can be used to predict the HDI of East Kalimantan Province is Holt's Double Exponential Smoothing (DES). The results obtained from DES Holt forecasting of HDI data for East Kalimantan Province for 2023-2027 are 77.95; 78.46; 78.98; 79.49; 80.01 with a Mean Absolute Percentage Error value of 0.229%.

METODE PEMBOBOTAN TF-IDF UNTUK KLASIFIKASI TEKS QUICK COUNT PEMILIHAN WAKIL PRESIDEN INDONESIA 2024 PADA X TWITTER DENGAN METODE SVM

2024-08-17T15:09:09+00:00

The 2024 Indonesian Vice Presidential Election Quick Count sparked diverse public reactions on X Twitter. The sheer volume and variety of expressed opinions complicate accurate sentiment identification and classification. This study aims to develop a text classification model using Support Vector Machine (SVM) to identify sentiment in election Quick Count-related tweets. Data was acquired through tweet collection, followed by pre-processing, word weighting using TF-IDF, and data splitting for model training and testing. Results indicated that the developed SVM model achieved 77.30% accuracy in tweet sentiment classification. The model's implementation is expected to aid in more effective information filtering and assist stakeholders in understanding public opinion more accurately.

PERBANDINGAN METODE K–NEAREST NEIGHBOR (KNN) DAN NAIVE BAYES TERHADAP ANALISIS SENTIMEN PADA PENGGUNA E-WALLET APLIKASI DANA MENGGUNAKAN FITUR EKSTRAKSI TF-IDF

2024-08-15T14:43:03+00:00

This research compares the accuracy of the K-Nearest Neighbor (KNN) and Naive Bayes methods in classifying user sentiment towards the DANA e-wallet application using Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction. User review data was collected through web scraping techniques and labeled by linguists and lexicon models. After undergoing pre-processing steps such as case folding, cleaning, tokenizing, stopword removal, and stemming, the data was classified using the KNN and Naive Bayes methods. The research results indicate that data labeling by linguists significantly improves the accuracy of both classification methods. Additionally, using TF-IDF as a word weighting method proves effective in enhancing the performance of sentiment classification models. Sentiment analysis of user reviews of the DANA application reveals various complaints and issues faced by users, providing information that can be used to improve the features and services offered, thereby increasing user satisfaction. This research also provides a comparison between the KNN and Naive Bayes methods, which can serve as a reference for other researchers in selecting appropriate methods for sentiment analysis on similar datasets.

PERBANDINGAN NILAI AKURASI DISTILBERT DAN BERT PADA DATASET ANALISIS SENTIMEN LEMBAGA KURSUS

2024-07-11T00:44:48+00:00

Penelitian ini bertujuan untuk menerapkan Analisis Sentimen dalam Ulasan Kursus dengan menggunakan pendekatan Transfer Learning menggunakan model bahasa DistilBERT dalam konteks pengembangan sistem pendidikan. Dengan pertumbuhan yang pesat dalam domain e-learning dan layanan kursus online, pemahaman pengguna terhadap berbagai kursus menjadi semakin penting bagi institusi pendidikan. Metode transfer learning, yang mengandalkan model-model NLP yang sudah terlatih seperti DistilBERT, telah terbukti efektif dalam tugas analisis sentimen dengan kinerja yang baik dan efisiensi yang tinggi.

Dengan peningkatan minat pada pembelajaran online, penelitian ini menginvestigasi bagaimana pendekatan analisis sentimen dapat memberikan wawasan yang lebih dalam terhadap ulasan kursus. Dengan penerapan teknik DistilBERT, diharapkan sistem mampu efektif dalam mengekstrak sentimen yang terkandung dalam ulasan tersebut, memberikan pemahaman menyeluruh terkait pendapat dan perasaan pengguna terhadap kursus yang mereka ikuti.

Melalui penelitian ini, diharapkan dapat memberikan kontribusi penting bagi penyelenggara kursus dalam meningkatkan kualitas layanan pendidikan yang mereka tawarkan, memberikan umpan balik yang lebih terperinci dan tepat waktu kepada pengguna. Diharapkan diseminasi hasil penelitian ini memberikan pandangan yang lebih luas mengenai penerapan transfer learning dalam analisis sentimen, terutama dalam konteks ulasan kursus

ARIMA (AUTOREGRESSIVE INTEGRATED MOVING AVERAGE) SEBAGAI ALGORITMA PREDIKSI TINGKAT PEMBATALAN HEREGISTRASI MAHASISWA BARU DI UNIVERSITAS X

2024-08-15T14:38:58+00:00

The digitalization era has transformed education, impacting new student admissions in Indonesia, which has various universities: State, Official, Religious, and Private. These universities share common procedures for admitting new students: file selection, test selection, and re-registration. However, many new students cancel their re-registration due to financial constraints, distance, or choosing another campus. Some students neglect the re-registration process until the deadline passes, affecting the accreditation of study programs and the reputation of the campus. To address this issue, a prediction model for re-registration cancellation rates can evaluate campus performance in attracting new students. The ARIMA algorithm (AutoRegressive Integrated Moving Average) is proposed as a suitable prediction model for time series data. This model can help universities identify and address factors leading to re-registration cancellations, thereby improving their performance and reputation. Using the SEMMA (Sample, Explore, Modify, Model, Assess) data mining methodology, the research produced an evaluation matrix with RMSE (Root Mean Square Error) values for various features: "non_registered" (145.77), "parents_income" (0.84), "parents_job" (4.07), and "entrance" (0.16). Additionally, the correlation matrix revealed two variables with a high influence on the target: "entrance" (0.85) and "parents_income" (0.68).

KLASIFIKASI SENTIMEN X-TWITTER PERIHAL PEMINDAHAN IBU KOTA INDONESIA MENGGUNAKAN EKSTRAKSI FITUR TF-IDF DAN METODE SUPPORT VECTOR MACHINE (SVM)

2024-08-15T14:44:12+00:00

The classification model has reached the realm of sentiment classification to analyze user sentiment in providing comments. this research aims to classify sentiment regarding the topic of moving the capital city of Indonesia using the Support Vector Machine (SVM) method with TF-IDF weighting. SVM has its own advantages, namely to overcome complex problems in SVM classification using the kernel function. the kernel functions to transform input data into a high dimensional feature space, allowing linear separation of data more easily. there are 3 sentiment categories in this study, namely Negative, Neutral and Positive sentiment. to determine these 3 categories, researchers used expert labelling services. the purpose of this study using the SVM method and TF-IDF feature extraction is to find out and analyze the accuracy results obtained in processing sentiment data regarding the transfer of the capital city of Indonesia. The accuracy results obtained are 64%, this shows that the SVM method with TF-IDF weighting is able to classify sentiment data with fairly good results.

SISTEM PAKAR APLIKASI DIAGNOSA PENYAKIT DALAM BERBASIS WEBSITE

2024-08-14T05:24:51+00:00

An internal medicine expert system is an application designed to assist in the process of diagnosing diseases based on symptoms experienced by patients. In today's digital era, the use of web-based expert systems is growing because it provides wider accessibility to users. This research aims to implement a website-based internal medicine expert system as a diagnosis tool for the general public. This system development method involves the steps of needs analysis, system design, implementation, and evaluation. In the needs analysis phase, data on disease symptoms and related medical information were collected to build the expert system knowledge base. Based on the analysis, a user-friendly website interface was designed as well as an algorithm for matching symptoms with corresponding diseases. Implementation was done using web technologies such as HTML, CSS, and JavaScript to build an interactive and responsive user interface. System evaluation was conducted through functionality and diagnosis accuracy trials involving a number of sample disease cases. The evaluation results show that the web-based internal medicine expert system is able to provide a fairly accurate diagnosis according to the symptoms entered by the user. Thus, the implementation of this system can be an effective solution in helping people to make an initial diagnosis of the disease.