Publication Search

Background: Public opinion analysis has become increasingly important in the digital era, where social media platforms generate large-scale textual data reflecting public perceptions toward environmental policies. Advances in Natural language processing (NLP) and machine learning enable systematic sentiment classification to support data-driven decision-making. Objective: This study aims to evaluate the effectiveness of several sentiment classification models in analyzing Indonesian-language social media data related to environmental policies. Method: The research employed a text mining pipeline including data crawling, preprocessing (case folding, tokenization, stopword removal, and stemming), and vectorization using TF-IDF. Three classification models Logistic Regression, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) were trained and evaluated using accuracy and F1-score metrics. Results: Experimental findings indicate that LSTM achieved the highest performance with 91.7% accuracy and 91.2% F1-score, outperforming SVM (88.5%) and Logistic Regression (84.2%). Sentiment distribution analysis shows that public opinion is dominated by positive sentiment (47.5%), followed by neutral (32.0%) and negative (20.5%). Overall: The results demonstrate that deep learning-based models provide more robust contextual understanding and more reliable sentiment mapping for environmental policy analysis.

This study aims to analyze the effect of Corporate Social Responsibility (CSR) disclosure, Environmental Costs, and Company Size on the Financial Performance of mining sub-sector manufacturing companies listed on the Indonesia Stock Exchange. In this study using the type of quantitative data with the acquisition of secondary data derived from financial statements. Sampling using Purposive Sampling technique with 32 samples in this study. The method used in this study adopts the Partial Least Squares Structural Equation Modeling (PLS-SEM) method to analyze the relationship between CSR disclosure, Environmental Costs and Company Size. The results of this study indicate that Corporate Social Responsibility (CSR) has a positive but insignificant effect on financial performance. While Environmental Costs and Company Size have a negative and significant effect on Financial Performance.

This paper introduces a hybrid optimization approach that combines genetic algorithms with gradient descent for effective nonlinear function approximation in highdimensional data. Traditional methods struggle with computational efficiency and accuracy in such complex spaces. By integrating genetic algorithms to provide a global search strategy with gradient descent for finetuning, the proposed method achieves faster convergence and improved accuracy. Simulations and case studies demonstrate its effectiveness in applications like data mining, image recognition, and financial modeling.

This research aims to analyze the role of corporate social responsibility (CSR) disclosure and good corporate governance (GCG) in enhancing financial performance. This research model was tested using a sample from all mining sector companies listed on the Indonesia Stock Exchange during the period 2020-2022. The data analysis employed multiple linear regression and Generalized Least Square (GLS) methods to identify independent variables influencing the dependent variable in detecting indirect effects through financial performance proxied by ROA, EPS, and Tobin’s Q. The results of the study indicate that CSR has a positive effect on ROA, a negative effect on EPS, and no significant effect on Tobin’s Q. GCG proxied by independent board of commissioners, has a positive effect on ROA and Tobin’s Q. Audit committee has a positive effect on ROA and a negative effect on EPS and Tobin’s Q. Board of directors has a positive effect on EPS and Tobin’s Q but no significant effect on ROA.

The aim of this research is to identify and analyze the economic potential of the base sector so that economic growth in East Kutai Regency can increase. Classification of economic sectors that have advantages and potential and can be developed to boost economic growth in East Kutai Regency. An overview of the pattern and structure of economic growth in East Kutai Regency. This research uses quantitative secondary data. The approach used is the Location Quotient (LQ) analysis tool to identify economic sectors that are the base sectors, Shift Share analysis to identify economic sectors that have the potential to become leading sectors and Klassen Typology analysis to identify a picture of the pattern and structure of economic growth to support economic development and regional development in East Kutai Regency. The research results show that during the research period, namely from 2013 to 2022, the mining and quarrying sector still dominates the economic structure of East Kutai Regency with the contribution of this sector to the total GRDP of 83.37%. The Mining and Quarrying sector in East Kutai Regency is a basic sector, so changes in GRDP growth or policy changes in the mining and quarrying sector are believed to have an impact on the formation of GRDP as a whole and besides that, this sector also has competitive advantages and is included in the fast-growing sector. and grow fast. East Kutai Regency in 2013-2022 shows that there are eight economic sectors that have a negative sign (PPij < 0) or slow growth, namely the Agriculture, Forestry and Fisheries sectors amounting to Rp. – 53,630.94,-, Processing Industry sector Rp. – 117,477.84,-, Transportation and Warehousing sector Rp. – 24,119.22,-, Financial Services sector Rp. – 2,233.09, Real Estate sector Rp. – 10,176.60, Corporate Services sector Rp. – 1,288.94, Government Administration, Land and Mandatory Social Security sectors amounting to Rp. – 4,012.91, Education Services sector Rp. – 7,759.64,-. This happens because at the provincial level the growth of these sectors has slowed down, resulting in a slow growth impact on the same sectors in East Kutai Regency.

With the advent and rapid advancement of text mining technology, a computer-based approach used to capture sentiment standpoints from data in textual form is increasingly becoming a promising field. Detailed information about sentiment can be provided using aspect-based sentiment analysis, which can be used in better decision-making. This study aims to study, observe, and classify previous methods used in aspect-based sentiment analysis. A systematic review is adopted as the method used to collect and review papers to achieve this research's aim. Papers focused on sentiment analysis, aspect extraction, and aspect aggregation from different academic databases such as Scopus, ScienceDirect, IEEE Explore, and Web of Science were gathered based on the inclusion and exclusion criteria of the study. The gathered papers were further reviewed to answer the stated research questions. The findings from the research show the most used methods for aspect extraction, sentiment analysis, and aspect aggregation in aspect-based sentiment analysis. This research offers a robust synthesis of evidence to guide further academic exploration in sentiment analysis.

The increasing development of technology and increasing buying and selling activities require every business owner to adapt to technological developments, for business owners selling or processing sales data is very important as is done by PT.XYZ household furniture items such as tables, chairs, dressers, wardrobes, sofas and many more, where sales data is still done manually, such as a lack of reviewing what products consumers need and ineffective data storage. To overcome this problem the researcher tried to implement it using one of the methods available in data mining, namely the K-Means Algorithm. –certain data groups (clusters). So, by grouping this data, the company can find out which items are selling best and which are not selling well. So that the goods in the warehouse do not pile up. From this research, the resulting output is 5 of the best-selling items, and 5 of the least-selling items. With the data processing carried out, it is hoped that it can provide solutions to the company so that they can find out which items are the best-selling and best-selling items.

This research aims to determine financial performance, operational complexity, and good corporate governance mechanisms against audit delay. The sample for this research is 66 mining companies listed on the Indonesia Stock Exchange (BEI) from 2020 to 2022. The data in this research was obtained from secondary data originating from the company's financial reports and annual reports. The analytical method used in this research is multiple linear regression analysis. The results of this research test show that Profitability, Leverage, Operational Complexity, Audit Committee, and Institutional Ownership have no effect on Audit Delay. Meanwhile, the Board of Commissioners has a positive influence on Audit Delay.

Data from the Social Security Administering Agency (BPJS) for Employment in 2021 - 2022 recorded 499,604 cases of work accidents, then the Circular Letter of the Chief Mining Inspector number: B- 6234/MB.07/DBT.KP/2023 dated 9 October 2023 regarding Increasing Vigilance in Efforts Preventing Mining Accidents and Improving Mining Safety Performance, throughout 2023, 46.9% of accidents will result in deaths due to interaction activities on mine roads. Based on preliminary studies at PT. The true Saptaindra Site SERA in 2023 found that the number of property damage accidents (equipment damage) was 11 cases and near misses were 4 cases. The aim of this research is to identify risks that can occur both in terms of humans, the environment and operational processes, then be able to analyze the level of risk and provide recommendations for controlling dangerous risks to minimize the potential for work accidents at the PT Saptaindra Sejati Site SERA. This research uses HIRA (Hazzard Identification Risk Assessment) method with the main focus being able to identify potential hazards through calculating the level of opportunity (Likelihood) and level of severity (Saverity) in order to obtain the level of risk using a risk matrix. And then control is carried out according to the work safety hierarchy, namely elimination, substitution, engineering, administration and PPE (personal protective equipment). The results of this research show that after controlling jobs with a medium risk level, there are 3 jobs including Topsoil removal, Over burden removal and Coal getting and less than 9 according to table 2.3 Risk Matrix and jobs with a low risk level. risk), namely 3 jobs including Land clearing, Drill and blast and Mine water pumping work in the sump.    

The health Social Security Administering Agency (BPJS) is a legal entity specifically assigned by the government to administer social security. Seen in the vision and mission of the Long Term Develompment Plan For the Health Sector 2005-2025, namely that the community is expacted to have the ability to access quality health services and also obtain heald insurance, namely that the community gets protection in meeting their basic health needs. Especially for the people of Binjai city, to see the level of satisfaction of peolbe using BPJS Health in the city of Binjai, it is necessary to build a clustering that can group the level of satisfaction in each domicile. Data Mining Grouping using the K-Menas Clustering algoritma metdhod, which is a process of processing quite large amounts of data using statistical methods, this producing a group of data. It is hoped that clustering can complete the grouping of satisfaction levels of BPJS user commuites in the city of Binjai. There are 400 data from correspondent responses from the community regarding the level of satisfaction in using BPJS Health in the city of Binjai. From the results of trials with 400 data carried out with MATLAB, it was found that group 3, cluster 1, had 244 data, cluster 2 had 69 data, cluster 3 had 87 data, group 4 cluster 1 has 78 data, cluster 2 68 data, cluster 3 has 109 data, group 5 cluster 1 has 63 data, cluster 2 has 63 data, cluster 3 has 145 data, cluster 4 has 24 data, cluster 5 has 100 data.

XYZ is a multi-disciplinary company operating in the fields of mining contracts, engineering, procurement and construction as well as oil and gas services. This business entity, which has been established since 1972, has a strong commitment to Occupational Safety and Health (K3) which has become a culture in every element of the company. Basically, K3 is an effort to prevent/avoid/reduce accidents by stopping/removing/eliminating risks (risks). K3 is one of the requirements for increasing employee work productivity, this is closely related to achieving work or production targets. This research was conducted at the company PT. XYZ in the Balikpapan area. The aim of this research is to measure the level of employee concern for K3, with the efforts that the company has made through the rewards system, digitalization and audio-visual campaign methods. The research population is employees of PT. XYZ in the Balikpapan area. Sampling was carried out using a two-stage multi-stage cluster random sampling technique. The first stage is separated based on department cluster; Asset Management, SHE, SCM, HCBS, and Finance. The second stage is PT employees. XYZ is separated based on work environment stratification; office and field. Respondent data was analyzed with SEM-PLS using Smart PLS 3.0 software. The model developed illustrates that the rewards system, digitalization and audio-visual campaigns have a positive influence on worker safety motivation and indirectly influence worker safety behavior through worker safety motivation which acts as a mediating variable. Meanwhile, work safety motivation has a positive effect on work safety behavior.    

The following study aims to analyze and find out (1) The impact of incentives on the work results of PT employees. Amanah Safari Internasional Tour Travel, which has been running, (2) This research uses a qualitative approach to look for incentives to improve the performance of PT employees. Amanah Safari International Travel. Data mining methods encompass observation, documentation, and direct interviews with management and relevant staff. The results of this study show (1) the incentive system that the company has to provide material and non-material incentives to its employees, such as bonuses and social security, religious and non-religious awards and joint holidays. Employee quality, employee quantity, and employee attendance or discipline drive employee performance and motivation. This research shows that incentives can increase work morale and increase achievement, loyalty, discipline, and accountability towards positions. These valuable results can have an impact on improving employee performance. (2) According to the analysis results, PT. Amanah Safari Internasional Tour Travel has an incentive program that suits the needs of its employees, but further research is needed to improve the efficiency of this program. As a result, companies are expected to be able to maintain and improve their incentive policies to improve employee performance.

Biometric features that can be used for identification include iris, voice, DNA and fingerprints. Fingerprints are the most widely used biometric feature because of their uniqueness, universality and stability. Fingerprint recognition can be grouped into two different forms of problems, namely verification and identification. Verification is comparing one fingerprint with another fingerprint. Meanwhile, identification is matching an input fingerprint with fingerprint data in the database. Thus, identification can be interpreted as an extension of verification carried out by comparing one fingerprint to many fingerprints. Identification is inherently more complex than verification. The problem increases as the number of fingerprint datasets increases, resulting in an increase in the time required for the identification process. However, there is a way to overcome this complexity, namely classification. Apart from that, evolutionary algorithm optimization can also be carried out. The Chromosome Algorithm is an improvement on the evolutionary algorithm with a separate local search process. The memetic or chromosomal algorithm is a simple algorithm with reliable performance that can provide accurate solutions to problems in the real world. The current challenge is with the increasing growth of datasets (more than 106) which include the process of clustering text analysis, molecular DNA simulation, feature selection, and forecasting, handling large-scale optimization such as complex simulations, data mining, quantum chemistry, spectroscopic analysis, geophysical analysis, drug discovery, and fingerprint recognition studies. Chromosome algorithms have proven to be very competitive in large-scale optimization because they are based on stochastic algorithms that do not require gradient information.  

In Indonesia, tourism still has an important role in supporting national development. Morotai Island as a border area has a huge local potential in mining, farming, plantation, including human resources and tourism. Therefore, this research aimed to provide a recommendation for tourism development and so that to improve tourism competitiveness, particularly tourism activity conducted by tourists, based on SWOT analysis. This research used descriptive qualitative method. The research location was in the territory of Daruba, South Morotai, Morotai Island District, North Maluku Province. The data were obtained by doing observation, interview and literature study. In the interview part, some staff of Tourism Board and local people became the sources through focus group discussion and direct interview referred to purposive sampling technique. The SWOT analysis shows that Morotai Island District has nature beauty and War World II historical ruins as the strength. Those still have a huge opportunity to develop so that to revive the tourist activity there. Not to mention, Kelapa Bido as an endemic plant in Morotai Island District. Based on the SWOT analysis and observation, the recommendations for tourism activity are managing tour packages, agrotourism and digital tourism via augmented and virtual reality.  

Coal is one of the energy sources in the world. Coal is a very complex mixture of organic chemicals containing carbon, oxygen and hydrogen in a carbon chain. Sindang Marga Village is one of the villages in Bayung Lencir sub-district, Musi Banyuasin Regency, South Sumatra province. Based on survey data, it is known that the number of people in the village is 1,700 people, including those who do not yet have identity cards. After the establishment of a mining company, it is hoped that it will be able to raise the level of socio-economic conditions for the people of Sindang Marga village, both those without families and those with families. If people's income increases, of course the level of community welfare will also improve. The aim of this research was to determine the economic and social impact on society of PT activities. Waletindo Setia Persada in Sindang Marga Village, Bayung Lencir District, Musi Banyuasin Regency. This research is field research with a qualitative type of research. Data collection techniques use observation, interviews and documentation. The data analysis technique used is qualitative descriptive analysis, which consists of three activity streams, namely data reduction, data presentation and drawing conclusions. The research results show that the impact resulting from the activities of PT. Waletindo Setia Persada in Sindang Marga Village is a change in the livelihoods of the people of Sindang Marga Village from the agricultural sector to the mining sector, increasing micro businesses and minimizing unemployment. The existence of the Company also causes an increase in income and changes people's standard of living for the better. There are changes in behavior patterns in society, both positive and negative, such as income disparities, disruption of public roads, health problems and conflict.

Starting in June 2023, the government imposed a ban on exports of bauxite seeds. It aims to develop the value of bauxite which could subsequently boost the economy as well as the country's income. The aim of this study is to provide a better understanding of the impact of the bauxite export ban policy on the performance of mining companies in Indonesia, by comparing the company's performance before the policy and after the policy. This study uses secondary data, which is the financial data of three major companies in Indonesia as of 10 June for the period from 2018 to 2023 that exports bauxite. The research results from the paired sample t test analysis show that the ban on bauxite exports has no significant effect, which means that the policy has no negative effect on the average performance of mining companies in Indonesia.

Semen Z is one of the largest cement supplier companies in Indonesia and will continue to increase every year. The development of the cement industry is in line with the continued development of infrastructure projects, both private and Indonesian government. PT. Semen Z has good integration from raw material providers to cement that is ready to be used by every project that requires it. Development of PT. Cement Z will occur in the quantity of raw materials, human resources, and production processes, up to distribution to consumers. The activities carried out are land clearing/stripping, blasting, excavation and loading, as well as transportation and destruction. Raw materials sourced from this mining process include limestone, silica stone and clay. In this study mining was only carried out on limestone and clay was obtained from suppliers. The units used in the inventory data are limestone and clay raw materials (tons), ammonium nitrate chemicals (tons), diesel fuel (liters), electricity (kWh), emissions (tons), B3 waste (tons), non-B3 waste (tons) and products (tons). Every activity process carried out will have an impact on the environment, so the Company's commitment to a green industry or clean industry is required. To determine the environmental impact analysis on cement production activities, the Company conducted an environmental impact analysis using the Life Cycle Assessment (LCA) method. The aim of this research is to identify improvements in environmental performance, especially those that are hotspots in the Company's production process. The research results show that the highest identification of environmental impacts is obtained from activities at the Limestone mine, in accordance with the Pareto rules approach where if the contributors are more than 80% of the food it will affect the results of the impact analysis obtained.

Literary psychology is a branch of psychology that studies the interaction between psychology and literature. It involves analyzing and understanding how psychological elements, such as emotion, motivation, perception, and personality, can be understood through literary works. Literary psychology tries to explain and understand human experiences expressed in literary works, as well as how literary works can influence and affect readers emotionally and psychologically. "Analysis of Psychological Factors that Influence Consumer Decisions in Choosing the Modern Market: Data Mining Approach using RapidMiner" - Research This aims to find out which psychological factors influence consumer decisions in choosing modern markets. The type of research carried out is explanatory research which explains the causal relationship between variables through hypothesis testing. In this research, analysis of the coefficient of determination is carried out to determine consumer psychological factors. which contributed 62.1% in influencing purchasing decisions, while the remaining 37.9% was influenced by other factors in analysis using the Decision Tree method: This method is used to build prediction models based on decision trees. Decision trees can help identify the psychological factors that are most influential in making consumer decisions.

This study aims to examine and analyze the influence of institutional ownership, characteristics of the board of commissioners on risk management disclosures on the existence of a risk management committee (RMC). The population in this study are mining companies and various industries listed on the IDX in 2021, namely 102 companies. The sampling technique uses a purposive sampling method and the results are only 45 companies that are included in the sample criteria. Data analysis technique uses logistic regression. The test results show that institutional ownership and independent commissioners have no effect on the existence of a risk management committee (RMC), while education, experience and disclosure of risk management have an effect on the presence of a risk management committee (RMC). These results indicate that risk management should be carried out by the company to develop a follow-up strategy so that business continuity is maintained under the supervision of the board of commissioners and included in the company's annual report.

PT. Kalonika Bara Kusuma is a company operating in the mining sector located in the city of Samarinda, East Kalimantan province. To achieve maximum profits, PT. Kalonika Bara Kusuma adds or subtracts units according to the amount of turnover obtained in the previous month. However, after being evaluated, it turned out that this method was not effective. Because you only see at a glance the fluctuations in historical data. Sometimes when you have reduced units, it turns out that demand in the following month actually increases. This results in less than optimal profits because they cannot serve existing customer requests. Vice versa. This is what causes PT. Kalonika Bara Kusuma experienced difficulty in making a decision to add or subtract units. From this problem, the author created an application that can predict the amount of turnover in the next month and provide recommendations for deciding which camera units should be increased or decreased in number. To predict the amount of turnover using the Multiple Linear Regression method. After obtaining the predicted results for the amount of turnover, a test was carried out using the Mean Absolute Percentage (MAPE) with a result of 200%, which means that the Multiple Linear Regression method is not suitable to be used to predict the amount of turnover in the next period. Production forecasting is a form of decision making that is used as a basis in many manufacturing and service industries. Therefore, companies that are able to produce products on time and in the right quantities are companies that are able to survive the competition. This demand forecasting is used to forecast demand for products that are independent (not dependent), such as forecasting finished products. The multiple linear regression method is an analytical technique that tries to explain the relationship between two or more variables, especially between variables that contain cause and effect, called regression analysis. So in relation to the description above, this research aims to determine production forecasting using the multiple linear regression method at PT. Kalonica Bara Kusuma.The mining industry is a series of activities that have a long period of time and costs a lot of money, a series of industrial activities, namely mining activities which include digging, loading and hauling to obtain optimal profits from activities. One of the mining industries needs to be a study of operational costs for transportation equipment