Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Sentiment Analysis for the 2024 DKI Jakarta Gubernatorial Election Using a Support Vector Machine Approach
No full textThis study analyzes public sentiment regarding candidates in the 2024 DKI Jakarta Gubernatorial Election utilizing a Support Vector Machine (SVM) approach. Recognizing the pivotal role of social media, particularly Twitter, in shaping public opinion, the research addresses the challenges of processing large volumes of unstructured data. Through systematic data preprocessing and feature extraction, the SVM model was applied, achieving a sentiment classification accuracy of 70%. The analysis revealed a distribution of sentiments where 36.1% of comments were positive, 33.4% negative, and 30.5% neutral. These findings illustrate the complexities of public discourse surrounding key political events, highlighting the model\u27s efficacy and the nuances of sentiment detection. Moreover, discussions on model limitations elucidate areas for enhancement, suggesting future avenues including the adoption of more sophisticated algorithms and improved data processing techniques. This research contributes to the understanding of voter sentiment dynamics in a significant electoral context, providing insights that may assist campaign strategies and political analyses in Indonesia
User Interface Evaluation of the Sumber Alam Ekspres Application Using the Heuristic Evaluation Method
No full textThe Sumber Alam Ekspres mobile application is designed to facilitate users in booking bus tickets. Since its launch in December 2020, the app has garnered over 35,000 downloads, averaging 48 downloads per day. Currently, it holds a rating of 4.1 out of 5 on the Google Play Store. User reviews—207 in total—reveal various complaints, particularly regarding mismatched information, malfunctioning features, and unintuitive interface design. To investigate these issues, a usability evaluation was conducted using the Heuristic Evaluation Method with 20 respondents representing different user types and statuses. The evaluation revealed that only one usability principle—Visibility of System Status—achieved a high score (69%). Six heuristics received moderate ratings: Match Between System and the Real World (62.5%), User Control and Freedom (56.5%), Consistency and Standards (53.5%), Error Prevention (52.5%), Recognition Rather Than Recall (59.5%), and Aesthetic and Minimalist Design (63.5%). Meanwhile, three heuristics were rated low: Flexibility and Efficiency of Use (42%), Help Users Recognize, Diagnose, and Recover from Errors (37%), and Help and Documentation (38%). These findings highlight specific areas for improvement in the user interface, particularly in providing adequate guidance, improving efficiency, and ensuring a more intuitive user experience.The Sumber Alam Ekspres mobile application is designed to facilitate users in booking bus tickets. Since its launch in December 2020, the app has garnered over 35,000 downloads, averaging 48 downloads per day. Currently, it holds a rating of 4.1 out of 5 on the Google Play Store. User reviews—207 in total—reveal various complaints, particularly regarding mismatched information, malfunctioning features, and unintuitive interface design. To investigate these issues, a usability evaluation was conducted using the Heuristic Evaluation Method with 20 respondents representing different user types and statuses. The evaluation revealed that only one usability principle—Visibility of System Status—achieved a high score (69%). Six heuristics received moderate ratings: Match Between System and the Real World (62.5%), User Control and Freedom (56.5%), Consistency and Standards (53.5%), Error Prevention (52.5%), Recognition Rather Than Recall (59.5%), and Aesthetic and Minimalist Design (63.5%). Meanwhile, three heuristics were rated low: Flexibility and Efficiency of Use (42%), Help Users Recognize, Diagnose, and Recover from Errors (37%), and Help and Documentation (38%). These findings highlight specific areas for improvement in the user interface, particularly in providing adequate guidance, improving efficiency, and ensuring a more intuitive user experience
Development of a Performance Model for SMEs to Go International in Aceh Barat Regency to Strengthen the Coastal Economy
No full textThis study examines the relationships between export orientation, social capital, strategic competitiveness, and export performance within the context of firms operating in international markets. Utilizing a theoretical framework based on the Resource-Based View (RBV) and Cadogan\u27s epistemology, the research explores the role of social capital as an intangible resource that can enhance export performance and the contribution of export orientation as a driver of strategic competitiveness. The analysis results reveal a significant impact of export orientation on strategic competitiveness (P-Value 0.000), yet it does not demonstrate a direct significant effect on export performance (P-Value 0.139). Conversely, social capital has a highly significant impact on export performance (P-Value 0.000) and export orientation (P-Value 0.000), but it does not significantly influence strategic competitiveness (P-Value 0.249). Furthermore, strategic competitiveness significantly affects export performance (P-Value 0.000). These findings suggest that while both export orientation and social capital play vital roles in enhancing export performance, firms must develop robust strategic competitiveness to achieve success in the global market. This research provides insights into the importance of integrating social resources, export orientation, and competitive strategies to achieve optimal export performance
The Effect of Return on Assets, Debt to Equity, and Total Asset Turnover on Earnings Growth with Company Size as a Moderating Variable in Basic Industry and Chemical Sector Manufacturing Companies Listed on the Indonesia Stock Exchange (IDX) for the 2020-2023 Period
No full textThis study aims to test and analyze the effect of return on assets, debt to equity, and total asset turnover on earnings growth with company size as a moderating variable in manufacturing companies in the basic and chemical industry sectors listed on the Indonesia Stock Exchange (IDX) for the period 2020-2023. The study population was 170 companies. The method used in sampling based on criteria (purposive sampling) obtained 49 companies as samples with a total of 196 observations. The secondary data collection method includes annual financial reports, journals, and related books. This research is quantitative, data analysis is done through PLS-SEM with a two-stage test approach using the Smart PLS 3.0 program. The results showed that return on assets and debt to equity partially had a significant positive effect on earnings growth while total asset turnover partially did not affect earnings growth. Company size is unable to moderate return on assets, debt to equity, and total asset turnover on earnings growth. The implication of this research is to provide insight for company management to pay more attention to the efficiency of asset use and capital structure management to increase profit growth, as well as provide information for investors in considering financial factors before making investment decisions in basic and chemical industry sector companies
The Effect of Quality of Work Life, Competence, Communication, Career Development, and Motivation on Employee Performance At PT. Bank BRI (Bank Rakyat Indonesia) Aek Nabara District
No full textThis study analyses the Influence of Quality of Work Life, Competence, Communication, Career Development, and Motivation on Employee Performance at PT. Bank BRI (Bank Rakyat Indonesia) Aek Nabara District. Data collection techniques used in the study were observation, documentation, and questionnaires using a Likert scale. The population in this study was 35 employees of PT. Bank BRI (Bank Rakyat Indonesia) Aek Nabara District. The entire population in this study will be used as a sample, namely 35 employees. The study\u27s results prove that Quality of Work Life positively and significantly affects Employee Performance. Competence has a positive and significant effect on Employee Performance. Communication has a positive and significant effect on Employee Performance. Career Development has a positive and significant effect on Employee Performance. Motivation has a positive and significant effect on Employee Performance at PT. Bank BRI (Bank Rakyat Indonesia) Aek Nabara District
Analysis of Public Sentiment Towards President Prabowo\u27s Work Program Using The CNN
Get PDFDigital media has now become the primary means for Indonesians to receive and respond to information, including the work programs presented by Prabowo Subianto. One of the programs that is widely discussed by the public is related to efforts to improve the national economy. Public responses to this issue are widespread on social media, reflecting diverse sentiments. Therefore, this study aims to analyze the sentiment of comments from social media users X regarding President Prabowo\u27s work programs in the economic sector, using a deep learning approach based on the Convolutional Neural Network (CNN) architecture. The methods employed include data collection, text preprocessing, and training a CNN model. The dataset used consisted of 2,467 data points, with 1,086 labeled as positive and 1,381 labeled as negative. The test results showed that the model achieved an accuracy of 87.45% and an Area Under the Curve (AUC) score of 0.9373, indicating excellent classification performance in distinguishing between positive and negative sentiments. This study proves that the combination of CNN and FastText is a practical approach to understanding text-based public opinion from social media
dalam, pada Peran Komik Strip “Proyek Molor” dalam Strategi Pemasaran Digital pada Perusahaan GoCement
No full textThe digital revolution has completely changed the way companies approach marketing, especially in industries such as construction that have traditionally relied on conventional methods. Since then, comic strips have been seen as an effective medium to build brand identity and connect with audiences. Their unique combination of visuals and storytelling cuts through the noise of digital content, making complex topics accessible and memorable. This study examines how GoCement, as a progressive construction platform, has integrated comic strips into its digital marketing strategy. Using Robin Landa\u27s structured design approach, a five-stage process (orientation, analysis, conception, design and implementation) was used to create a comic strip that aligns with GoCement\u27s brand values. The goal of the project was to increase engagement, with audiences not only interacting more frequently but also retaining brand messages for longer. Insights from this project show how a comic titled “Project Molor” can remind and educate readers how to use the GoCement app to avoid mistakes. This approach offers a way to balance education, promotion and entertainment, creating specialized content that appeals to both experts and newcomers. This strategy highlights the growing importance of creative visual storytelling in B2B marketing, where standing out and being remembered is just as important as consumer-facing campaigns.Revolusi digital telah sepenuhnya mengubah cara perusahaan melakukan pendekatan pemasaran, terutama di industri seperti konstruksi yang secara tradisional mengandalkan metode konvensional. Sejak saat itu, komik strip dipandang sebagai media yang efektif untuk membangun identitas merek dan terhubung dengan audiens. Kombinasi unik antara visual dan cerita yang mereka miliki mampu menembus kebisingan konten digital, membuat topik-topik yang kompleks menjadi mudah diakses dan mudah diingat. Studi ini meneliti bagaimana GoCement, sebagai platform konstruksi yang progresif, telah mengintegrasikan komik strip ke dalam strategi pemasaran digitalnya. Dengan menggunakan pendekatan desain terstruktur dari Robin Landa, proses lima tahap (orientasi, analisis, konsepsi, desain, dan implementasi) digunakan untuk membuat komik strip yang selaras dengan nilai-nilai merek GoCement. Tujuan dari proyek ini adalah untuk meningkatkan keterlibatan, dengan audiens yang tidak hanya berinteraksi lebih sering tetapi juga mempertahankan pesan-pesan merek lebih lama. Wawasan dari proyek ini menunjukkan bagaimana komik berjudul “Proyek Molor” dapat mengingatkan dan mengedukasi pembaca cara menggunakan aplikasi GoCement untuk menghindari kesalahan. Pendekatan ini menawarkan cara untuk menyeimbangkan edukasi, promosi dan hiburan, membuat konten khusus yang menarik bagi para ahli dan pendatang baru. Strategi ini menyoroti semakin pentingnya penceritaan visual yang kreatif dalam pemasaran B2B, di mana penampilan yang menonjol dan teringat sama pentingnya dengan kampanye yang berhadapan langsung dengan konsumen
Analisis Teknik Facial Expression oleh Animator 3D: Studi Kasus Proyek Animasi X
Get PDFThe rapid development of 3D animation highlights the importance of realistic facial expressions for non-verbal communication and narrative emotion, making it necessary to research urgent shot handling techniques on relevant facial expressions. However, the production is often hampered due to technical challenges, such as the X Animation Project at PT Kinema Systrans requires special handling related to urgent shot handling techniques that require detailed notes and uniformity of facial expression handling by animators. This research uses an art-based research method with a qualitative approach that analyzes the results of urgent shot notes on the facial rig model free character Mr. Vincent. Based on the findings of the urgent shot notes, there are various terms that need to be addressed in facial expression problems. These notes indicate specific areas that need to be improved in the workflow of making facial expressions.Pesatnya perkembangan animasi 3D menyoroti krusialnya ekspresi wajah realistis untuk komunikasi non-verbal dan emosi naratif, menjadikan perlunya riset teknik penanganan urgent shot animasi pada ekspresi wajah yang relevan. Namun, dalam produksinya sering terhambat karena adanya tantangan teknis, seperti pada X Animation Project di PT Kinema Systrans membutuhkan penanganan khusus terkait teknis penanganan urgent shot yang membutuhkan catatan detail serta keseragaman penanganan ekspresi wajah yang dilakukan oleh animator. Penelitian ini menggunakan metode art based research dengan pendekatan kualitatif yang menganalisis hasil catatan urgent shot pada facial rig model free character Mr. Vincent. Berdasarkan hasil temuan pada catatan urgent shot terdapat berbagai istilah yang perlu ditangani pada permasalahan facial expression. Catatan temuan ini mengindikasikan area spesifik yang perlu diperbaiki dalam alur kerja pembuatan ekspresi wajah
Topic Modeling of Skincare Comments from Female Daily
Get PDFThe increasing popularity of skincare products in Indonesia has encouraged many consumers to seek and share information through online platforms. One of the most influential platforms is Female Daily, which provides a space for users to review and discuss various skincare products. This study aims to explore the dominant topics within user-generated comments related to skincare products on Female Daily. The research employed a descriptive qualitative approach using topic modeling with Latent Dirichlet Allocation (LDA). Data were collected from user comments on several popular skincare products and were preprocessed through punctuation removal, case folding, tokenization, normalization, stopword removal, and stemming. The optimal number of topics was determined using coherence scores. The results reveal that users frequently discuss personal experiences, highlight product benefits and drawbacks, and often refer to their specific skin concerns. These insights provide valuable information for skincare brands to understand customer preferences and perceptions. In conclusion, topic modeling with LDA proves effective in extracting meaningful themes from large-scale textual data, offering a useful method for analyzing consumer feedback in the beauty industry.The increasing popularity of skincare products in Indonesia has encouraged many consumers to seek and share information through online platforms. One of the most influential platforms is Female Daily, which provides a space for users to review and discuss various skincare products. This study aims to explore the dominant topics within user-generated comments related to skincare products on Female Daily. The research employed a descriptive qualitative approach using topic modeling with Latent Dirichlet Allocation (LDA). Data were collected from user comments on several popular skincare products and were preprocessed through punctuation removal, case folding, tokenization, normalization, stopword removal, and stemming. The optimal number of topics was determined using coherence scores. The results reveal that users frequently discuss personal experiences, highlight product benefits and drawbacks, and often refer to their specific skin concerns. These insights provide valuable information for skincare brands to understand customer preferences and perceptions. In conclusion, topic modeling with LDA proves effective in extracting meaningful themes from large-scale textual data, offering a useful method for analyzing consumer feedback in the beauty industry
Sentiment Classification of MyPertamina Reviews Using Naïve Bayes and Logistic Regression
Get PDFThis research conducts a comparative evaluation of the effectiveness of the Naïve Bayes and Logistic Regression algorithms in mapping public perceptions of the MyPertamina application on the Google Play Store. The data consists of 2,000 user reviews obtained through a scraping technique. The research steps include labeling the reviews as positive or negative, followed by pre-processing and TF-IDF weighting. The dataset was systematically divided into two parts, with 80% allocated for model training and the remaining 20% for evaluation. The Naïve Bayes and Logistic Regression models were implemented using the Python programming language and evaluated based on accuracy, precision, recall, and F1-score metrics. The analysis shows that Logistic Regression achieved an accuracy of 86%, while Naïve Bayes achieved 81%. Logistic Regression demonstrated superior performance as it effectively captures linear relationships between features in TF-IDF representations and provides a more balanced outcome in terms of precision and recall. In contrast, Naïve Bayes is more influenced by high-frequency word distributions and does not account for feature correlations, which can limit its performance in certain contexts. Therefore, Logistic Regression is considered more suitable for sentiment classification tasks in this study. These findings emphasize the importance of selecting appropriate algorithms for sentiment analysis and suggest opportunities for future research using alternative methods to enhance predictive accuracy.This research conducts a comparative evaluation of the effectiveness of the Naïve Bayes and Logistic Regression algorithms in mapping public perceptions of the MyPertamina application on the Google Play Store. The data consists of 2,000 user reviews obtained through a scraping technique. The research steps include labeling the reviews as positive or negative, followed by pre-processing and TF-IDF weighting. The dataset was systematically divided into two parts, with 80% allocated for model training and the remaining 20% for evaluation. The Naïve Bayes and Logistic Regression models were implemented using the Python programming language and evaluated based on accuracy, precision, recall, and F1-score metrics. The analysis shows that Logistic Regression achieved an accuracy of 86%, while Naïve Bayes achieved 81%. Logistic Regression demonstrated superior performance as it effectively captures linear relationships between features in TF-IDF representations and provides a more balanced outcome in terms of precision and recall. In contrast, Naïve Bayes is more influenced by high-frequency word distributions and does not account for feature correlations, which can limit its performance in certain contexts. Therefore, Logistic Regression is considered more suitable for sentiment classification tasks in this study. These findings emphasize the importance of selecting appropriate algorithms for sentiment analysis and suggest opportunities for future research using alternative methods to enhance predictive accuracy