Claim Missing Document
Check
Articles

Sentiment Analysis of DANA Application Reviews on Google Play Store Using Naïve Bayes Classifier Algorithm Based on Information Gain Cindy Caterine Yolanda; Syafriandi Syafriandi; Yenni Kurniawati; Dina Fitria
UNP Journal of Statistics and Data Science Vol. 2 No. 1 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss1/147

Abstract

DANA is a digital payment platform that provides various features to make it easier for users to make payments, transfers, and balance replenishment online. DANA application users provide a variety of reviews that include both constructive and critical opinions, which can be valuable input for DANA application developers. The purpose of this research is to evaluate the results of sentiment classification of DANA application user reviews on the Google Play Store service using the Naïve Bayes Classifier method and Information Gain feature selection. In addition, this study aims to assess the effect of applying IG feature selection on the performance of the resulting model. In this study, reviews are divided into two categories, namely positive and negative based on lexicon-based labeling. Furthermore, data weighting, feature selection, and data division are carried out with a proportion of 80% train data and 20% test data before model building. There are two models, namely a model without feature selection (NBC model) and a model with feature selection (NBC-IG model). The evaluation results showed that the NBC model with 1106 features performed well, with 82.91% accuracy, 83.96% precision, and 90.23% recall. Meanwhile, the NBC-IG model with 536 features showed higher performance, with 85.09% accuracy, 85.79% precision, and 92.09% recall. The application of IG feature selection with the IG value limit parameter > 0.01 in the NBC model successfully reduced the number of features by 570, and improved model performance with an increase in accuracy by 2.18%, precision by 1.83%, and recall by 1.86%.
Twitter Data Sentimen Analysis 2024 Presidential Candidate Using Algorithm Naïve Bayes Classifier By Methods K-Fold Cross Validation Aldi Prajela; Syafriandi Syafriandi; Dony Permana; Dina Fitria
UNP Journal of Statistics and Data Science Vol. 2 No. 1 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss1/149

Abstract

Indonesia implements a democratic system by involving the public in General Elections (Pemilu) for specific political positions. The active community expresses opinions on social media, especially regarding the 2024 Presidential Election (Pilpres) and respective presidential candidates, which have become trending topics on Twitter. The analysis used to absorb these tweets into information is sentimen analysis using the Naïve Bayes Classifier algorithm with the K-fold Cross-Validation method. Through the stages of pre-processing, weighting, labeling, classification using NBC, and testing using a Confusion Matrix, The results of the classification from NBC showed that Anies got 80% positive tweets and 20% negative tweets from 1186 tweets, Prabowo Subianto got 78% positive tweets and 22% negative tweets from 1149 tweets, and Ganjar Pranowo got 77% positive tweets and 23% negative tweets from 1075 tweets. Testing process was carried out using the NBC algorithm with the K-Fold Cross Validation method using values k=1 to k=10. The function of K-Fold Cross Validation is to maximize the confusion matrix result. It can be conclude that Anies Baswedan has the highest score in iteration 4, namely a precision value of 90%, a recall value of 99%, and the accurary value of 91%. Furthemore, Ganjar Pranowo had the highest score in iteration 9, namely a precision value of 95%,a recall value of 97%, and an accuracy value of 92%. Meanwhile, Prabowo Subianto had the highest score in iteration 9, namely a precision value of 97%, a recall value of 99%, and an accuracy value of 94%.
Sentiment Analysis Using Support Vector Machine (SVM) of ChatGPT Application Users in Play Store Muthia Sakhdiah; Admi Salma; Dony Permana; Dina Fitria
UNP Journal of Statistics and Data Science Vol. 2 No. 2 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss2/158

Abstract

The ChatGPT application is an Articial Intelligence (AI) technology that responds to conversations in form text and voice messages, and is accessible via smartphones or computers. The ChatGPT provides answers and solutions related to the problems asked, the speed and complexity of the answers are also added values of this application. However, there are negative impacts, one of which is the vulnerability of scientific papers to plagiarism. Because of this, there are many reviews from the community that assess this application. These reviews can be seen on the Play Store which can be a reference before downloading the ChatGPT application. How the community responds can be seen through sentiment analysis, which will classify positive and negative assessments. Making it easier for companies to evaluate products. Then classification is carried out using Support Vector Machine (SVM), the classification model obtained is used to classify user reviews of the ChatGPT application. The results showed an accuracy of 93.9% with a linear kernel, and the sentiment of people who use the ChatGPT application is more positive.
Artificial Neural Networks to Forecasting the Retail Price of Beras Solok in Padang City using Backpropagation Algorithm Putri Rivani; Tessy Octavia Mukhti; Dodi Vionanda; Dina Fitria
UNP Journal of Statistics and Data Science Vol. 2 No. 2 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss2/168

Abstract

Strengthening rice production is an important step as the population continues to grow. Padang City is only able to meet 30% of the community's needs, so to fulfill the community's needs, rice is also imported from Solok. Forecasting can be done especially in order to see the movement of the average retail price of Anak Daro Solok Rice in Padang City which has decreased and increased in rice prices due to the lack of rice availability in Padang City. In this research, the forecasting method that will be used is the Artificial Neural Network Backpropogation Algorithm. Artificial Neural Networks are widely used for forecasting nonlinear time series data. Based on the results of the research that has been done, forecasting the average retail price of Anak Daro Solok Rice in Padang City using the Backpropagation Algorithm Artificial Neural Network obtained the optimal network architecture has the best model, namely BP (1,6,1) which model produces a MAPE of 0.03121%, indicating that the network performance of the model that has been formed shows very good results because it manages to achieve an accuracy rate (MAPE) of less than 10%. Artificial Neural Network Model based on Backpropagation Algorithm can be applied to predict the average retail price of Anak Daro Solok Rice in Padang City. Comparison of the results of forecasting the average retail price of Anak Daro Solok Rice in Padang City for the next 12 months period, namely an increase from the previous 12 months period.
Pemetaan Intensitas Gempa Bumi di Wilayah Sumatera Barat Menggunakan Model Epidemic Type Aftershock Sequence Spatio-Temporal Hidayatul Fikra; Dina Fitria; Nonong Amalita; Tessy Octavia Mukhti
UNP Journal of Statistics and Data Science Vol. 2 No. 2 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss2/171

Abstract

The random spatial and temporal occurrence of earthquakes means that this are still being researched from a seismological and stochastic perspective. Point processes are examples of stochastic processes which explain seismic activity, one of them is Epidemic Type Aftershock Sequence (ETAS) model. It lackness ignores the location or spatial component of. Consequently, the components of time, location, and magnitude will be taken into consideration when discussing the ETAS model in this study. The spatio-temporal model is the name given to this concept. Therefore, in this research,mapping of earthquake intensity will be carried out in the West Sumatra region using the spatio-temporal ETAS model stated in conditional intensity function with eight parameters. The data used are earthquake events in the West Sumatra region with a magnitude threshold of 4 SR and a depth of ≤ 70 km for the period January 2000 to January 2024. Parameter model estimated using the maximum likelihood method and solved using the Davidon Fletcher Powell algorithm. The result shows area of West Sumatra with high earthquake intensity is coastal area, namely West Pasaman, Padang, Mentawai Islands and the South Pesisir. This makes the area vulnerable to seismic disasters
PEMODELAN INDEKS PEMBANGUNAN GENDER (IPG) PROVINSI JAWA BARAT DENGAN PENDEKATAN REGRESI NONPARAMETRIK DERET FOURIER DHEA PUTRI RIZKIA; Fadhilah Fitri; Dony Permana; Dina Fitria
UNP Journal of Statistics and Data Science Vol. 2 No. 2 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss2/174

Abstract

Gender equality is a development target in many countries. The ideal condition in human development that is expected is that male and female population groups have equal access to play a role in development, control over existing development resources, and receive benefits from development equally and fairly. The gender gap still occurs today in all aspects. The condition of the gender gap can be known by looking at the Gender Development Index . In observing the data curve, between the Gender Development Index and each independent variable does not form a certain pattern. In addition, the data patterns that are formed tend to repeat. Nonparametric regression analysis is the solution. Fourier series is a nonparametric analysis used for repetitive data. Modeling was performed using 1, 2, and 3 oscillation parameters. Of the three parameters, the best model resulted from the K=3 oscillation parameters with a GCV value of 2.8084 and a coefficient of determination of 42.39%.
PENGEMBANGAN DATA NAGARI TANJUNG GADANG MENUJU DESA DIGITAL Yenni Kurniawati; Dina Fitria; Admi Salma
Pelita Eksakta Vol 6 No 2 (2023): Pelita Eksakta, Vol. 6, No. 2
Publisher : Fakultas MIPA Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/pelitaeksakta/vol6-iss2/210

Abstract

Developing villages' data toward digital data is one of villages' government programs to improve the villages. The village's government needs collaboration with professional surveyors and data digital builders to achieve the goal, which the government is unable to provide. The Statistics Department provided the team to overcome the problems by giving training surveys to local residents and accompanying them to build Nagari Tanjung Gadang digital data.
Development of an IoT-Integrated Cigarette Smoke Detection System Using MiCS-5524 Sensor Aminullah, Moh.Wahyu; Dina Fitria; Imam Akbar; Rama Denata
International Journal of Research in Vocational Studies (IJRVOCAS) Vol. 4 No. 1 (2024): IJRVOCAS - April
Publisher : Yayasan Ghalih Pelopor Pendidikan (Ghalih Foundation)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53893/ijrvocas.v4i1.243

Abstract

Cigarette smoke is one of the primary causes of indoor air pollution, leading to various adverse health impacts. To address this issue, this research aims to design of a cigarette smoke detection device using the MiCS-5524 sensor integrated with the Internet of Things (IoT). This device can detect the level of cigarette smoke in indoor spaces and provide alerts through an LCD, a buzzer, and the Blynk application. Furthermore, the device can activate an exhaust fan to remove cigarette smoke from the room. The device employs the NodeMCU ESP8266 microcontroller as the central control unit for system operation and internet communication. The MiCS-5524 sensor was chosen for its high sensitivity to carbon monoxide (CO), a major component of cigarette smoke. Test results demonstrate that the device functions effectively and accurately in detecting cigarette smoke and responding to indoor air conditions. It is anticipated that this device will contribute to improving indoor air quality and human health.
Classification of Harvest - Non Harvest in Rice Plant Image Using Convolutional Neural Network Algorithm Revina Rahmadani; Yenni Kurniawati; Dony Permana; Dina Fitria
UNP Journal of Statistics and Data Science Vol. 2 No. 3 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss3/181

Abstract

The Area Sample Framework (ASF) survey is an area based survey carried out by direct observation of sample parts whose locations have been determined. Every month ASF officers take photos of observation results using an Android based cellphone, where the results of the photos will be classified manually by supervision officers and sent to a central server for processing. The large amount of rice plant image data included can hinder officers in classifying rice growth phases. Therefore, to speed up the classification process, the Convolution Neural Network (CNN) method is used. In this research, the CNN model built consists of 3 convolution layers, 3 pooling, ReLU and Sigmoid activation functions, with several other parameters such as batch size and epoch value. The training results show that the accuracy value for the training data is 92.86% with an epoch value of 120. Meanwhile, the accuracy value for the validation data is 69.01%. Model evaluation shows a precision value of 21.34% and a recall value of 32.20%. This shows that the CNN model has poor performance in predicting harvest and non-harvest in rice plant images.
Analysis of the Population of Sumatera Island Using Profile Analysis Sri Rahayu; Dony Permana; Yenni Kurniawati; Dina Fitria
UNP Journal of Statistics and Data Science Vol. 2 No. 3 (2024): UNP Journal of Statistics and Data Science
Publisher : Departemen Statistika Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/ujsds/vol2-iss3/185

Abstract

The distribution of the population in each province according to age groups in Sumatra Island has tended to change over time. Therefore, an analysis is needed to provide a comparative overview of the characteristics between the populations of each province with different age groups. This analysis can help to understand the variations in these characteristics in relation to the population. Profile analysis is a technique within multivariate analysis of variance that can be used to examine the differences between two or more populations, where each population is influenced by several treatments (variables) tested. This method has been applied in various fields, including government, to understand the characteristics of specific regions. This study aims to identify the characteristics of the population in each province on the island of Sumatra based on sixteen age groups. Sumatra is one of the largest islands in Indonesia, comprising ten provinces. In this research, profile analysis is utilized to compare the population profiles of each province in Sumatra based on the sixteen age groups. Based on the profile parallelism test, it was found that the profiles of the ten provinces are not parallel, indicating differences in the average population numbers or trend patterns among the provincial profiles in Sumatra based on age groups. Further testing using Tukey's HSD method was conducted to compare each pair of provinces based on specific age groups. The testing revealed that there are significant differences in several provinces in Sumatra for each age group.