Claim Missing Document
Check
Articles

Found 5 Documents
Search

Sentiment Analysis of Suicide on X Using Support Vector Machine and Naive Bayes Classifier Algorithms Mardianto, M. Fariz Fadillah; Pratama, Bagas Shata; Audilla, Marfa; Pusporani, Elly
INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Vol 9 No 1 (2025): February 2025
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/intensif.v9i1.23742

Abstract

Background: The World Health Organization (WHO) defines health as a state of physical, mental, and social well-being, not just the absence of disease. Mental health, essential for overall well-being, is often neglected, leading to disorders like depression, a major cause of suicide. In Indonesia, suicide cases have surged, with 971 reported from January to October 2023. Objective: This study aims to analyze public sentiment regarding the rise in suicide cases in Indonesia using sentiment analysis methods, specifically Support Vector Machine (SVM) and Naive Bayes Classifier (NBC). The findings are expected to raise public awareness and provide policy recommendations to support mental health initiatives. Methods: One method used to understand public perception regarding the issue of suicide is text mining. This research employs text mining techniques with the Support Vector Machine (SVM) and Naive Bayes Classifier algorithms to analyze public sentiment related to suicide cases in Indonesia. Data was collected from tweets on social media platform X using crawling methods with snscrape and Python, totaling 1,175 tweets. Results: The results indicate that the Linear SVM model achieved higher accuracy than Naive Bayes in classifying tweet sentiments, with an accuracy rate of 80%. Conclusion: The SVM algorithm with a linear kernel achieved 80% accuracy and an identical ROC-AUC score. Word cloud visualization highlighted terms like "kill," "self," "depression," and "stress" as key negative sentiments. This study aims to raise public awareness and support better mental health policies in Indonesia.
A Comparison of Multivariate Adaptive Regression Spline and Spline Nonparametric Regression on Life Expectancy in Indonesia Pratama, Bagas Shata; Suliyanto, Suliyanto; Mardianto, M. Fariz Fadillah; Sediono, Sediono
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 9, No 3 (2025): July
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v9i3.29413

Abstract

Life expectancy is a key indicator of a population’s overall health and well-being. It also reflects the effectiveness of government efforts in improving public welfare. Despite various initiatives by both the government and society to improve life expectancy in Indonesia, significant disparities remain. This quantitative study aims to support these efforts by analyzing factors influencing life expectancy in Indonesia using data from the Indonesian Central Agency of Statistics (BPS) in 2023. A comparative analysis was conducted using two methods: Multivariate Adaptive Regression Spline (MARS) and Spline Nonparametric Regression. The results show that the MARS model outperforms the Spline model, achieving a lower Mean Squared Error (MSE) of 1.183 and a higher R-Square of 82.7%. Key variables significantly influencing life expectancy include access to decent housing, access to safe drinking water, per capita expenditure, and the Gini ratio. The findings not only confirm the presence of complex interactions among predictor variables effectively captured by the MARS method, but also contribute to the existing literature by emphasizing the importance of socioeconomic determinants in health outcomes. From a policy perspective, the results suggest that government strategies should prioritize improving access to basic needs and reducing inequality. These insights can guide targeted, data-driven interventions aimed at enhancing life expectancy in Indonesia.
CATEGORICAL ANALYSIS TO PERCEPTIONS OF GOVERNMENT POLICY IN ELECTRICITY FUEL MANAGEMENT AS ALTERNATIVE TO SUBSTITUTE OIL FUEL USING CHI-SQUARE TEST Chamidah, Nur; Siregar, Naufal Ramadhan Al Akhwal; Al Farizi, Muhammad Fikry; Pratama, Bagas Shata; Faiza, Atikah; Fibryan, Muhammad Hilmi
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 17 No 3 (2023): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol17iss3pp1287-1300

Abstract

The scarcity and increase in world oil prices is a tough dilemma that must be responded to by the Indonesian government. In order to prevent fuel consumption from swelling, the government plans to reduce fuel subsidies. The plan certainly has many positive impacts, including savings on government finances so that they can be diverted to fund other programs that are more effective and on target. These savings are also useful in reducing the budget deficit, controlling the consumption of fuel oil, and saving non-renewable natural resources. It is appropriate for the state to think hard about switching energy to New and Renewable Energy (EBT) so that people's dependence on fossil energy consumption can be shifted. Therefore, this study aims to determine the current public perception of government policies in the management of fossil fuel energy so that they can be considered by the government in making comprehensive policy decisions. The data used in this study is in the form of primary data obtained from respondents with a population of Indonesian people and collected online through a questionnaire. The data analysis method in this study used the independence test with the chi-square test on categorical data. The results of this study indicate that there is a relationship between the level of public perception of the basic policy of managing electric fuel with the last level of education, type of work, and the area of the population.
COMPARISON OF LOCAL POLYNOMIAL REGRESSION AND ARIMA IN PREDICTING THE NUMBER OF FOREIGN TOURIST VISITS TO INDONESIA Pratama, Bagas Shata; Suryono, Alda Fuadiyah; Auliyah, Nina; Chamidah, Nur
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 1 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss1pp0043-0052

Abstract

Indonesia is a country that has a variety of exotic tourist destinations and can attract tourists to visit. Currently, tourism is one of the sectors that plays a major role in driving the Indonesian economy. Various tourists, both domestic and foreign, are expected to continue to increase in number every year. Therefore, appropriate policies are needed from the government to develop the tourism sector so that it can be even better over time. This research aims to predict the number of foreign tourist visits to Indonesia using the Autoregressive Integrated Moving Average (ARIMA) model and local polynomial regression. The data used in this research is the number of foreign tourist visits per month from January 2017 to December 2022 obtained from the the Kemenparekraf website. This data is fluctuating so that the method a local polynomial approach is appropriate for this study. The data analysis method used are local polynomial regression and ARIMA model. In the ARIMA model there are assumptions that must be met. In this study, the ARIMA model obtained has met the assumption of residual normality but does not meet the assumption of homoscedasticity so that ARIMA modeling cannot be continued and analysis is only carried out with local polynomial regression. The result of this study is a prediction of future tourist visits. The MAPE value of the local polynomial regression approach is 1.43% which is categorized as a prediction with high accuracy because the value is less than 10%. Thus, the local polynomial regression approach is very well used to predict the number of foreign tourist visits to Indonesia.
PREDICTION OF UNIT VALUE INDEX OF EXPORTS OF SITC 897 JEWELRY AND PRECIOUS GOODS GROUP IN INDONESIA Koesnadi, Grace Lucyana; Pratama, Bagas Shata; Ain, Dzuria Hilma Qurotu; Pusporani, Elly; Mardianto, M. Fariz Fadillah
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 4 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss4pp2247-2262

Abstract

Export is an international trade activity that plays an important role in the economic progress in Indonesia. One of Indonesia's leading commodities that dominate the export market is jewelry. In export activities, the export unit value index is an important component that serves to describe the development of export commodity prices. This unit value index always changes every time and fluctuates. This research conducts a comparative analysis of the performance of parametric method, non-parametric method, and machine learning, specifically, ARIMA, Fourier series estimator, and Support Vector Regression (SVR). This study aims to evaluate the effectiveness of various methods in improving prediction accuracy for the unit value index of the SITC code 897 in Indonesia. The research data used is secondary data including monthly export unit value index data with SITC code 897 in Indonesia obtained from the Central Bureau of Statistics. The data divided into 90% training data and 10% testing data. The methods used in this analysis are ARIMA, Fourier series estimator, and SVR. The best model obtained from each method is ARIMA (1,1,1) with MAPE of 10.92%, Fourier series estimator with MAPE of 8.47%, and an SVR RBF kernel function with MAPE of 3.73%. The results of this study obtained the best method for predicting the unit value index of SITC code 897 is SVR with an RMSE value of 8.288 and very good prediction accuracy.