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 research is based on an analysis of an American short story entitled The Lottery by Shirley Jackson. The purpose of this analysis is to examine and categorize the characterization of the character in the short story. The methods applied to analyze the data in this study is a qualitative method to describe in words the examination of the short story based on the characterization. The data source is collected through documentation and note-taking processes. For the results of this analysis the character in the short story classified into several types and detailed classifications of each character's traits, actions, and roles within the context of the narrative.

This research aims to improve the effectiveness of lung cancer classification performance using Support Vector Machines (SVM) with hyperparameter tuning. Using Radial Basis Function (RBF) kernels in SVM helps deal with non-linear problems. At the same time, hyperparameter tuning is done through Random Grid Search to find the best combination of parameters. Where the best parameter settings are C = 10, Gamma = 10, Probability = True. Test results show that the tuned SVM improves accuracy, precision, specificity, and F1 score significantly. However, there was a slight decrease in recall, namely 0.02. Even though recall is one of the most important measuring tools in disease classification, especially in imbalanced datasets, specificity also plays a vital role in avoiding misidentifying negative cases. Without hyperparameter tuning, the specificity results are so poor that considering both becomes very important. Overall, the best performance obtained by the proposed method is 0.99 for accuracy, 1.00 for precision, 0.98 for recall, 0.99 for f1-score, and 1.00 for specificity. This research confirms the potential of tuned SVMs in addressing complex data classification challenges and offers important insights for medical diagnostic applications.

This article has been retracted at the request of the Editor-in-Chief. The journal was alerted to issues within this article, including significant overlap in content, methodology, and visual materials with another previously published article: "Social Engineering Attack Classifications on Social Media Using Deep Learning" (DOI: 10.32604/cmc.2023.032373) published in Computers, Materials & Continua in 2023. Upon thorough investigation, it was found that the article substantially reproduces ideas, methodologies, and figures from the original work without proper attribution, violating the ethical standards of the journal and academic publishing. The authors were contacted and asked to provide an explanation for these concerns. The corresponding author acknowledged the oversight and accepted responsibility for the duplication. Consequently, the authors formally requested the withdrawal of the paper. As per journal policy, the Editor-in-Chief has decided to retract the article due to a breach of publication ethics. The journal sincerely regrets that these issues were not detected during the manuscript screening and review process and apologizes to the authors of the original article, as well as to the readers of the journal. For more information on the journal’s ethical policies, please visit: Retraction Policy.

The proliferation of imported used clothing trade is due to clothes sold having foreign brands at cheap prices so that people who want to stay fashionable prefer imported used clothes because they are considered more affordable. The Clinical Pathology Laboratory of Muhammadiyah University Surabaya stated that used clothing samples contained mold or yeast fungi, Staphylococcus aureus bacteria, Escherichia coli bacteria and HPV (Human Papilloma Virus). This study aims to investigate the regulations regarding the trade of secondhand clothing in Indonesia and explore the legal protection provided for consumers of secondhand clothing in the country. The study employed a normative juridical legal research method, utilizing both the statute approach and conceptual approach. It drew upon legal materials such as Law Number 8 of 1999, Law Number 36 of 2009, Law Number 7 of 2014, and Minister of Trade Regulation No. 18 of 2021. The initial finding of the research was that the importation of secondhand clothing in Indonesia has been prohibited under Minister of Trade Regulation No. 18 of 2021, Article 2, paragraph (3), while local secondhand clothing businesses are permitted based on the Indonesian Business Field Standard Classification (KBLI) with code 47742. Secondly, legal protection for secondhand clothing consumers in Indonesia has been regulated in Law Number 8 of 1999. One of the consumer rights that needs to be fulfilled in consumer protection is the right to compensation for losses suffered by consumers based on Article 4 number 8, Article 7 letter f, and Article 19 paragraph (1).

This study explores the utilization of LightGBM, a gradient-boosting framework, to classify the inhibitory activity of beta-secretase 1 inhibitors, addressing the challenges of Alzheimer's disease drug discovery. The study aims to enhance classification performance by focusing on overcoming the limitations of traditional statistical models and conventional machine-learning techniques in handling complex molecular datasets. By sourcing a dataset of 7298 compounds from the ChEMBL database and calculating molecular descriptors for each compound as features, we employed LightGBM in conjunction with a set of carefully selected molecular descriptors to achieve a nuanced analysis of compound activities. The model's efficiency was benchmarked against traditional machine-learning algorithms, revealing LightGBM's superior accuracy (84.93%), precision (87.14%), sensitivity (89.93%), specificity (77.63%), and F1-score (88.17%) in classifying beta-secretase 1 inhibitor activity. The study underscores the critical role of molecular descriptors in understanding drug efficacy, highlighting LightGBM's potential in streamlining the virtual screening process. Conclusively, the findings advocate for LightGBM's adoption in computational drug discovery, offering a promising avenue for advancing Alzheimer's disease therapeutic development by facilitating the identification of potential drug candidates with enhanced precision and reliability.

Indonesia's golden opportunity to take part in a world-class soccer competition at the U-20 World Cup competition was wiped out, as FIFA gave the decision to revoke Indonesia's status as host of the U-20 World Cup. Indonesian netizens who felt disappointed expressed their opinions and trended on social media Twitter. This research focuses on sentiment analysis of tweets using a combination of FastText embeddings method for word vectorization and using LSTM type RNN algorithm for sentiment classification. The dataset used totals 9,645 data consisting of 4,141 positive data and 5,504 negative data taken from March 29, 2023 to April 05, 2023. The test results on the LSTM model provide the best performance with an accuracy value of 74.92%, precision 74.74%, recall 74.92%, and f1-score 74.78%. The conclusion of this research is that the majority of datasets have negative sentiments, which means that people are more likely to give negative opinions than to provide support to Indonesian football which is experiencing problems. It is hoped that with this conclusion in the future people will better control their opinions and provide positive opinions when Indonesia is experiencing problems.

This research aims to determine the ability to organize compositions, process colors, adjust colors, and determine the level of suitability of shapes in the results of paintings using umbrella media at the Qalam Jihad Painting Studio Pematangsiantar. This research uses a qualitative descriptive method, by researching a topic in a systematic, factual and accurate manner obtained from data collection in the field and carried out based on existing facts and characteristics. This research is to review the composition, color and shape of paintings using umbrella media by studio students aged 13-15 years. The composition aspect gets the lowest score and the color aspect gets the highest score. This can be seen from the good coloring and color combinations with dark and light on the objects and colors that are seen clearly and appropriately by the studio students. Based on this, it produces a higher color aspect than other aspects. The classification of the results of reviewing the composition, color and shape of paintings using umbrella media at the Qalam Jihad Pematangsiantar painting studio is that 7 students are categorized as good with a score of 241.4 to 266 and an average score of 80.5 to 88.6. 8 students were quite good with scores of 211.2 to 234.9 with an average score of 70.4 to 78.3.  

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.

Within language, there are several categories, such as language politeness, which have objectives and intents that vary depending on the context and situation of human communication. In this language civility study, attention is drawn to the goals and intentions generally contained in our language usage. This study aims to identify forms of compliance and violations of the principle of language politeness on the Satu Persen playlist of Taman Edukasi: Career Preparation. This research uses two approaches, namely the qualitative descriptive approach as a methodological approach and the pragmatic approach as a theoretical approach. The technique used in collecting data is the listen-and-record technique. Data analysis of this research is presented through a data triangulation process, which includes three stages: data verification, data presentation, and data classification. The author conducted this research hoping that public knowledge about the principles of language politeness will be wider. This study aims to identify forms of compliance and violations of the principle of language politeness on the Satu Persen playlist of Taman Edukasi: Career Preparation. The results showed that in the playlist there were thimbles of generosity, wisdom, consensus, opinion, and sympathy thimbles. However, there is no thimble of apology, forgiveness, appreciation, simplicity, and feeling. Furthermore, the study's findings demonstrate the necessity for an increased awareness of the utilization of courteous and deferential language in communication, particularly concerning the realm of education and career readiness.

Education and human life cannot be separated, because education as a determinant of the direction of human life, the higher human education will show the higher quality of human life and vice versa. In line with the development of education, however, there are still people who reject the progress of education because they believe that the development of the times is not a guarantee for the realization of independence and peace of mind. This research aims to raise the issue of education development in Baduy community of Leuwidamar District, Lebak Regency, Banten Province. The Baduy community consists of groups, Inner Baduy, Outer Baduy and Muallaf Baduy, the three of them have their own uniqueness, for the Inner Baduy community they reject various forms of modernization, while the Outer Baduy community they accept although there is still a classification between what is accepted and what is rejected, while the Muallaf Baduy community totally accepts the development even their lifestyle is not like the lifestyle of urban communities, in terms of their children's education some of them have enjoyed higher education.

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.

In the agricultural sector, the automatic identification of chili pepper varieties is crucial for improving production efficiency and quality. This study developed a chili pepper variety detection system based on characteristics using the Principal Component Analysis (PCA) method. The PCA method was used to reduce the dimensionality of chili pepper image data, thereby facilitating the classification process while retaining the key features necessary for chili pepper variety identification. The recognition system for chili pepper identification involves inputting chili pepper image data into a computer. The computer then interprets and identifies the chili pepper variety, and the test data utilizes a dataset of chili pepper images from various varieties. The research results indicate that the proposed system achieves a high level of accuracy in detecting and classifying chili pepper varieties. Consequently, this system can assist farmers and agricultural industry stakeholders in the chili pepper sorting and selection process, thereby improving operational efficiency and the quality of the harvest.

The results of data classification and field surveys by Unsuri students in Wilayut Village, Sukodono District. Has potential MSMEs in the form of businesses that produce a product of goods or services. However, in marketing activities, business actors are still doing conventionally and the use of branding strategies is also not optimal. So that the scope of marketing is still limited, making the business being run unable to develop properly. KKN activities as a form of community service in Wilayut Village aim to provide social contributions from the campus to the community as well as for the community to get help with thoughts and energy to carry out village development and solve community problems in the village. The method used is the MSME data classification method and partner participation by providing direction on the benefits of social media. Participating in contributing to the classification of MSME data in Wilayut Village and helping business actors in increasing the existence of cilok kuah seblak bu tin as one of the MSMEs engaged in the food sector.

Abstract: Indonesia, which consists of thousands of islands, reaching 17,001 islands, is known as a maritime country because the ocean area is larger than the land area, around 2/3 of the total area of ​​Indonesia. Sea transportation as part of the National Transportation System needs to unite all regions of Indonesia. Maritime transportation accidents occur due to 3 (three) important factors, namely human error, technical factors and weather (natural) factors. The purpose of this research is to analyze the influence between the independent variables, namely the Role of Harbor Master, Communication Ability and ISM Code, for the dependent variable, namely Shipping Safety. The population in this study was 130 people consisting of ship crew and employees of the PT. ASDP Indonesia Ferry (Persero) Padang Bai Branch who had knowledge classification about shipping safety and the sample in this study was 100 respondents with the technique used was non-probability sampling technique namely by using quota sampling. The analytical method used is descriptive analysis and quantitative analysis, data is analyzed using multiple linear regression analysis with the help of the Statistical Package For Social Science (SPSS) software. The results of this research by testing the t-test hypothesis show that the variables Role of Harbormaster, Communication Ability and ISM Code have a positive and significant effect on shipping safety at the Padang Bai Bali Ferry Port. Based on the results of the research, it can be seen that the research model of the multiple linear regression equation is Y = 2.898 + 0.436X1 + 0.214X2 + 0.189X3 + µ. From the regression results, it can be seen that the variable that has the most dominant influence on shipping safety is the role of the harbor master variable with a regression coefficient of 0.436. With the r square test of 0.526 or 52.6%, which means that the increase in shipping safety at the Padang Bai Bali Ferry Port is influenced by the Role of the Harbor Master, Communication Ability and ISM Code, namely 52.6% and other factors that influence the increase in shipping safety at the Padang Ferry Port Bai Bali was 47.4%.

The research aims to find out what the emotional state of teenagers in novels is by using the theory of literary psychology according to David krech's book of emotional classification. It identifies the underlying emotions, the emotions associated with sensory stimulation, emotions related to self-assessment and emotions connected with others. This research method employs qualitative methods using descriptions, dialogues and characters that relate to the emotional reactions of characters. The results of analysis show that the novel's emotional main character has such basic emotions as happiness, anger, fear and sadness in various situations. This study provides insight into how the emotional condition of the novel can be perceived by the theory of David krech. This study may be a reference to further research on emotional states in literature.

Cultural development in Indonesia, driven by science and technology, places education as the key to achieving national goals. Focusing on the practice stage in educational technology provides practical experience at SMA Negeri 8 Maros. Informatics learning involves programming, artificial intelligence, and computer networks. Research at SMA Negeri 8 Maros involved 35 class X.5 students with a focus on Information and Communication Technology (ICT). Strengthening the Teaching Profession (P2K) from 4 September to 30 October 2023, creating innovative learning tools for the integration of office applications. Students are required to master office applications and online communication skills. The Pancasila student profile emphasizes critical thinking skills, independence and creativity. The results of implementing Informatics learning using the PBL model show a positive impact on student motivation, increasing enthusiasm, and building critical thinking skills. Students who apply PBL produce higher grades. Informatics learning classification is important for understanding computational thinking and computer systems. The application of the PBL model has a positive impact making students more creative and independent in creating projects using Microsoft Office.    

This study was conducted to analyze the classification of emotions of the main character in the novel 00.00 by Ameylia falensia using David Krech”s theory. The purpose of this tudy is determine the emotional  structure of the main characters in the novel that is the object of research. The concepts of gulit, seld-punishment, shame, hatred, and love become the main quotes in the novel 00.00 by Ameylia Falensia. The results showed that the main character in the novel experienced a wide range of emotions related to family problems and events. This study uses a comprehensive literary research methology to identify the emotional structure of the main characters and clasisify the emotions of the main characters in the novel that became the object og research. Thus, it can be concluded that the emotion of all Lengkara characters that is dominant arises in Lengkara, namely the emotion of sadness wich leads to aspects of losing something important to cause disappointment. While the less dominant emotion appears in Lengkara, namely the emotion of the concept of guilt which is characterized by aspects contrary to ethics and moral values.

In facing the increasing awareness of environmental impact, electric vehicles have become a primary focus in the global automotive industry. With the advancement of technology and the growing need for eco-friendly solutions, the evaluation of public sentiment towards electric vehicles becomes highly relevant. This research aims to analyze opinions expressed on Twitter regarding the use of electric vehicles using the Long Short Term Memory (LSTM) classification method. Utilizing a dataset of 30,000 entries, this study applies the LSTM algorithm to classify sentiment in tweets. Four different scenarios are tested, involving combinations of Continuous Bag of Words (CBOW) and Skip-Gram feature extraction methods, as well as data split percentages of 80:20 and 70:30. The research results demonstrate high accuracy levels across all scenarios, ranging from 85.16% to 85.9%. These findings indicate the effectiveness of sentiment analysis in gauging public perspectives on the use of electric vehicles. This study makes a significant contribution to understanding public sentiment related to electric vehicles based on Twitter data while highlighting the application of sentiment analysis techniques in the context of electric vehicle usage.

Mass communication, messages are called information or news. In presenting news, every media, especially online media, is required to always present news presentations that are able to attract readers in such a way. Issues in the news are conveyed through various media, one of which is online media. Likewise, Tempo media not only presents literacy media in the form of magazines, but also online media. The development of globalization and information has made it easy for various issues to spread, such as the issue of the existence of various gender terms currently, one of which is gender neutral which has become a news issue and is also an issue taken up by researchers. One of the gender neutral statements occurred in one of the UNHAS students as reported by Tempo.co. This research uses descriptive qualitative research methods. Data collection techniques use observation and documentation. The aim of this research is to analyze the framing in the news about the expulsion of Hasanuddin University students who claim to be gender neutral by the online media Tempo.co using the Pan and Kosicki model based on the classification of four syntactic, script, thematic and rhetorical structures. The results of this research are that if it is concluded from Pan and Kosicki's four structures, there are several points in the news published by Tempo.co, namely first, the pros and cons of gender neutral recognition by a student. Second, the lecturer's attitude violates the code of ethics. Third, Tempo.co's stance is pro gender deviation.