eJournal Komunitas Dosen Indonesia
Not a member yet
1406 research outputs found
Sort by
Evaluation of the E-Peken Surabaya Website Quality Using Modified Webqual 4.0 and Importance Performance Analysis
Full text linkE-Peken Surabaya is a web–mobile platform initiated by the Surabaya City Government to empower local economic actors, including MSMEs, food stalls (SWK), and local stores. Since its implementation in 2023, users have reported usability issues, highlighting the need for an evaluative study on service quality. This research adopts a descriptive-quantitative method using purposive sampling, with a total of 385 respondents selected based on active usage. Data collection employed a modified WebQual 4.0 questionnaire integrated with additional variables such as Reliability, Trust, Citizen Support, and Efficiency to capture comprehensive user perceptions. Data were analyzed using SPSS, with Pearson’s r for validity and Cronbach’s Alpha for reliability testing. Using Importance Performance Analysis (IPA), eight indicators were identified in Quadrant I (High Importance Low Performance), which require immediate strategic intervention. These include interface responsiveness (UI/UX), completeness and clarity of product information, accessibility of communication channels, consistency in system maintenance, and assurances in data privacy and security. These areas demonstrated significant negative gaps between perceived importance and performance, suggesting that user satisfaction is being compromised in core service aspects. The integration of WebQual 4.0 and IPA proves effective in isolating service components most in need of reform. As a strategic response, the study recommends incremental improvement planning, periodic performance audits, and scalable solutions to optimize user experience and enhance platform reliability
Evaluation of Information Security Management Capability Level with COBIT 5
Full text linkInformation security is a crucial aspect of information technology management, especially in government institutions such as the Department of Communication and Informatics (DISKOMINFO), which often faces challenges such as cyberattacks, lack of formal documentation, and limited resources in managing risks and securing data. These challenges hinder the organization’s ability to protect sensitive information and maintain public trust. This study evaluates the maturity level of information security governance at DISKOMINFO of Sampang Regency using the COBIT 5 framework, focusing on three domains: APO12 (Manage Risk), APO13 (Manage Security), and DSS05 (Manage Security Services). The method used is a case study with a descriptive qualitative approach through interviews and documentation. The results show that all three processes are at Level 1 (Performed Process), with 40.34% in the Partially Achieved category for APO12, 84.60% in the Largely Achieved category for APO13, and 57.23% in the Largely Achieved category for DSS05, where processes are carried out but not formally documented or standardized. There is a lack of monitoring and continuous improvement, making the governance reactive rather than proactive. Improvements are needed through development of policies, formal procedures, and more organized, sustainable security controls. Increasing employee awareness and allocating resources for information security are also critical. This research provides novelty by evaluating three COBIT 5 domains (APO12, APO13, DSS05) in a local government context, which has rarely been done. The findings offer a comprehensive maturity mapping as a strategic reference for improving information security governance in local government institutions.Information security is a crucial aspect of information technology management, especially in government institutions such as the Department of Communication and Informatics (DISKOMINFO), which often faces challenges such as cyberattacks, lack of formal documentation, and limited resources in managing risks and securing data. These challenges hinder the organization’s ability to protect sensitive information and maintain public trust. This study evaluates the maturity level of information security governance at DISKOMINFO of Sampang Regency using the COBIT 5 framework, focusing on three domains: APO12 (Manage Risk), APO13 (Manage Security), and DSS05 (Manage Security Services). The method used is a case study with a descriptive qualitative approach through interviews and documentation. The results show that all three processes are at Level 1 (Performed Process), with 40.34% in the Partially Achieved category for APO12, 84.60% in the Largely Achieved category for APO13, and 57.23% in the Largely Achieved category for DSS05, where processes are carried out but not formally documented or standardized. There is a lack of monitoring and continuous improvement, making the governance reactive rather than proactive. Improvements are needed through development of policies, formal procedures, and more organized, sustainable security controls. Increasing employee awareness and allocating resources for information security are also critical. This research provides novelty by evaluating three COBIT 5 domains (APO12, APO13, DSS05) in a local government context, which has rarely been done. The findings offer a comprehensive maturity mapping as a strategic reference for improving information security governance in local government institutions
Predicting Social Media Addiction Using Machine Learning and Interactive Visualization with Streamlit
Full text linkThe increasing use of social media among students has raised concerns regarding its impact on mental health, academic performance, and interpersonal relationships. This study introduces a Streamlit-based web application that predicts social media addiction levels using the Random Forest algorithm. The model incorporates variables such as daily usage hours, mental health scores, and conflicts caused by social media. The innovation of this approach lies in combining machine learning with interactive visualizations for real-time addiction prediction, providing a user-friendly, data-driven tool for early screening. Unlike traditional models that primarily rely on self-reported data or simple metrics, this method integrates multiple behavioral and psychological indicators to improve prediction accuracy. The model outperforms linear regression in all key metrics, achieving an R² value of 0.9903, which explains 99.03% of the variation in addiction scores. It also reports a low Mean Absolute Error (MAE) of 0.0370, Mean Squared Error (MSE) of 0.0244, and Root Mean Squared Error (RMSE) of 0.1561, highlighting its accuracy. Black-box testing showed an average error of just 0.354% in predictions and confirmed that the app’s features function effectively across devices. These findings emphasize the potential of this application as an effective tool for identifying students at risk of social media addiction, enabling timely interventions, and offering a foundation for future improvements through real-time data integration and advanced machine learning models.The increasing use of social media among students has raised concerns regarding its impact on mental health, academic performance, and interpersonal relationships. This study introduces a Streamlit-based web application that predicts social media addiction levels using the Random Forest algorithm. The model incorporates variables such as daily usage hours, mental health scores, and conflicts caused by social media. The innovation of this approach lies in combining machine learning with interactive visualizations for real-time addiction prediction, providing a user-friendly, data-driven tool for early screening. Unlike traditional models that primarily rely on self-reported data or simple metrics, this method integrates multiple behavioral and psychological indicators to improve prediction accuracy. The model outperforms linear regression in all key metrics, achieving an R² value of 0.9903, which explains 99.03% of the variation in addiction scores. It also reports a low Mean Absolute Error (MAE) of 0.0370, Mean Squared Error (MSE) of 0.0244, and Root Mean Squared Error (RMSE) of 0.1561, highlighting its accuracy. Black-box testing showed an average error of just 0.354% in predictions and confirmed that the app’s features function effectively across devices. These findings emphasize the potential of this application as an effective tool for identifying students at risk of social media addiction, enabling timely interventions, and offering a foundation for future improvements through real-time data integration and advanced machine learning models
Development of a Web-Based Extracurricular Information System Using the Waterfall Model
Full text linkExtracurricular activities are an important part of the holistic development of students which includes the formation of character, interests, talents, and social skills. However, many educational institutions still manage these activities manually through spreadsheets and printed documents, resulting in data duplication, information delays, and low transparency. This research aims to design and develop a web-based extracurricular information system to support the administration, monitoring, and evaluation of activities in an efficient and structured manner. The development of the system uses the Waterfall model chosen for its sequential and well-documented workflow, suitable for systems with predefined needs from the outset. The development stages include needs analysis, system design using UML, implementation with Laravel 9 and MySQL, as well as testing through the Black Box method and direct evaluation by the end user. The results of the Black Box test show that all system features are working according to specifications. Additionally, feedback from users shows a high level of satisfaction with the ease of use, navigation, and relevance of the features provided. This system successfully overcomes administrative challenges in managing extracurricular activities and is able to improve operational efficiency and user engagement. With the support of features such as automatic periodic assessments, PDF reports, notifications to parents, as well as a multilingual interface, the system has the potential to be more widely adopted by educational institutions that have similar contexts.Extracurricular activities are an important part of the holistic development of students which includes the formation of character, interests, talents, and social skills. However, many educational institutions still manage these activities manually through spreadsheets and printed documents, resulting in data duplication, information delays, and low transparency. This research aims to design and develop a web-based extracurricular information system to support the administration, monitoring, and evaluation of activities in an efficient and structured manner. The development of the system uses the Waterfall model chosen for its sequential and well-documented workflow, suitable for systems with predefined needs from the outset. The development stages include needs analysis, system design using UML, implementation with Laravel 9 and MySQL, as well as testing through the Black Box method and direct evaluation by the end user. The results of the Black Box test show that all system features are working according to specifications. Additionally, feedback from users shows a high level of satisfaction with the ease of use, navigation, and relevance of the features provided. This system successfully overcomes administrative challenges in managing extracurricular activities and is able to improve operational efficiency and user engagement. With the support of features such as automatic periodic assessments, PDF reports, notifications to parents, as well as a multilingual interface, the system has the potential to be more widely adopted by educational institutions that have similar contexts
Platform An E-Commerce Platform for Coffee MSMEs: System Design and Basic Features
No full textDigitalization of Micro, Small, and Medium Enterprises (MSMEs) has emerged as a strategic necessity in the era of digital transformation. However, many coffee-based MSMEs in Indonesia continue to rely on third-party marketplace platforms that limit autonomy over customer data, pricing control, and brand personalization. This study aims to address these constraints by designing and developing an independent, web-based e-commerce system that aligns with the specific operational needs of coffee MSMEs particularly those seeking low-cost, user-friendly solutions that enable direct customer engagement and reduce commission-based dependencies. The system was developed using Laravel for the backend and Vite.js for the frontend, adhering to the sequential stages of the waterfall model: requirements analysis, system design, implementation, and testing. Key features include product catalog management, shopping cart functionality, manual payment upload, and product review integration. Black-box testing confirmed that all features operated without critical errors under typical usage conditions. Usability testing conducted with five MSME users resulted in an average satisfaction score of 4.23 out of 5 (83%), with high ratings for ease of navigation and interface responsiveness. Performance metrics, including average page load time (<=3 seconds), device compatibility, and user flow scalability, met expected standards. Although the current system employs manual payment validation, future enhancements will focus on integrating secure payment gateways, real-time analytics dashboards, and modular APIs. In summary, the platform offers a practical and scalable e-commerce solution tailored to the autonomy and contextual demands of Indonesia's coffee MSMEs.Digitalization of Micro, Small, and Medium Enterprises (MSMEs) has emerged as a strategic necessity in the era of digital transformation. However, many coffee-based MSMEs in Indonesia continue to rely on third-party marketplace platforms that limit autonomy over customer data, pricing control, and brand personalization. This study aims to address these constraints by designing and developing an independent, web-based e-commerce system that aligns with the specific operational needs of coffee MSMEs particularly those seeking low-cost, user-friendly solutions that enable direct customer engagement and reduce commission-based dependencies. The system was developed using Laravel for the backend and Vite.js for the frontend, adhering to the sequential stages of the waterfall model: requirements analysis, system design, implementation, and testing. Key features include product catalog management, shopping cart functionality, manual payment upload, and product review integration. Black-box testing confirmed that all features operated without critical errors under typical usage conditions. Usability testing conducted with five MSME users resulted in an average satisfaction score of 4.23 out of 5 (83%), with high ratings for ease of navigation and interface responsiveness. Performance metrics, including average page load time (<=3 seconds), device compatibility, and user flow scalability, met expected standards. Although the current system employs manual payment validation, future enhancements will focus on integrating secure payment gateways, real-time analytics dashboards, and modular APIs. In summary, the platform offers a practical and scalable e-commerce solution tailored to the autonomy and contextual demands of Indonesia's coffee MSMEs
Implementation of Technique for Order Preference by Similarity to Ideal Solution for Selecting Content
Full text linkThis study addresses the challenge faced by the Sukabumi Creative Hub Instagram team in identifying the most engaging content by proposing a web-based Decision Support System (DSS) utilizing the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. Instagram, as a dominant social media platform in Indonesia, serves as a vital tool for promoting local creative industries, yet current content evaluation lacks systematic analysis. The system developed ranks 62 content items based on three engagement metrics—likes, views, and shares—weighted at 5, 3, and 1 respectively. Data were processed using Microsoft Excel and visualized through an Input-Process-Output (IPO) model. The results show that “Rekap Merangkum Sukabumi” achieved the highest relative closeness (RC = 0.8793), demonstrating TOPSIS’s effectiveness in ranking content based on proximity to ideal engagement levels. Compared to previous studies that applied TOPSIS in different contexts, this research offers a novel contribution by applying it to localized social media content, filling a gap in digital content analytics literature. Despite limitations such as subjective weighting, platform specificity, and manual calculations, the system offers a replicable, structured approach to content evaluation, with implications for improved social media strategy and future research in automated, cross-platform DSS applications. Ultimately, this study bridges practical needs in creative content management with theoretical development in decision support systems for digital engagement analysis.This study addresses the challenge faced by the Sukabumi Creative Hub Instagram team in identifying the most engaging content by proposing a web-based Decision Support System (DSS) utilizing the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. Instagram, as a dominant social media platform in Indonesia, serves as a vital tool for promoting local creative industries, yet current content evaluation lacks systematic analysis. The system developed ranks 62 content items based on three engagement metrics—likes, views, and shares—weighted at 5, 3, and 1 respectively. Data were processed using Microsoft Excel and visualized through an Input-Process-Output (IPO) model. The results show that “Rekap Merangkum Sukabumi” achieved the highest relative closeness (RC = 0.8793), demonstrating TOPSIS’s effectiveness in ranking content based on proximity to ideal engagement levels. Compared to previous studies that applied TOPSIS in different contexts, this research offers a novel contribution by applying it to localized social media content, filling a gap in digital content analytics literature. Despite limitations such as subjective weighting, platform specificity, and manual calculations, the system offers a replicable, structured approach to content evaluation, with implications for improved social media strategy and future research in automated, cross-platform DSS applications. Ultimately, this study bridges practical needs in creative content management with theoretical development in decision support systems for digital engagement analysis
Implementation of Content-Based Filtering in a Novel Recommendation System to Enhance User Experience
Full text linkThis study addresses a critical challenge in digital novel platforms: the difficulty of delivering personalized and accurate recommendations due to limited user interaction data. This limitation often leads to irrelevant or generic suggestions, which can diminish user engagement and hinder content discovery. The significance of solving this issue lies in enhancing user experience by ensuring that readers are presented with novels that truly align with their interests, even in the absence of extensive behavioral data. To overcome this problem, the study proposes an innovative hybrid recommendation system that integrates Content-Based Filtering (CBF) with the Random Forest algorithm. The system generates personalized recommendations by analyzing novel attributes such as title, genre, score, and popularity. The methodology involves extracting features from textual data using Term Frequency-Inverse Document Frequency (TF-IDF), followed by the calculation of cosine similarity to assess title relevance. These similarity scores are then combined with popularity predictions derived from the Random Forest model to produce final recommendations that reflect both content similarity and statistical relevance. The proposed system demonstrates strong performance, achieving an accuracy of 94.0%, precision of 81.4%, recall of 80.3%, and an F1-score of 80.8%. These results underscore the system’s capability to deliver accurate and diverse suggestions. By enhancing personalization and addressing the limitations of conventional CBF systems, this hybrid approach offers practical value for digital novel platforms. It serves as an effective tool for improving content discovery, increasing reader satisfaction, and supporting user retention in content-rich environments
Personality Prediction Based on Video Using Transfer Learning DeepID Model
Full text linkThis research presents an automatic personality prediction system based on the Big Five model openness, conscientiousness, extraversion, agreeableness, and neuroticism by leveraging transfer learning on the DeepID architecture. Video input is first processed with the MTCNN algorithm for robust facial region detection under varying lighting and poses. Extracted features are fed into a modified DeepID model, pre-trained on large-scale face-recognition datasets, to perform spatial encoding. To capture temporal dynamics, Long Short-Term Memory (LSTM) networks model frame-to-frame changes in expression. Training and validation use the ChaLearn LAP dataset of approximately 10,000 annotated videos. Experimental results demonstrate 88.6% overall accuracy, with an average precision of 87.2%, recall of 86.5%, and F1-score of 86.8%, confirming the model’s balanced performance across classes. A minimum loss of 11.3% further underscores effective convergence. The complete pipeline is deployed via Flask, enabling real-time, web-based integration. Beyond academic novelty, this system holds promise for practical applications: in recruitment, it can offer unbiased, rapid personality screening; in mental-health contexts, it may assist clinicians by flagging behavioral cues non-invasively; and in human–computer interaction, adaptive interfaces could personalize responses based on users’ inferred traits. By combining transfer learning with temporal modeling, our approach delivers a scalable, non-invasive tool for automated psychological assessment through visual data, paving the way for ethical, real-time personality analytics in diverse domains.This research presents an automatic personality prediction system based on the Big Five model openness, conscientiousness, extraversion, agreeableness, and neuroticism by leveraging transfer learning on the DeepID architecture. Video input is first processed with the MTCNN algorithm for robust facial region detection under varying lighting and poses. Extracted features are fed into a modified DeepID model, pre-trained on large-scale face-recognition datasets, to perform spatial encoding. To capture temporal dynamics, Long Short-Term Memory (LSTM) networks model frame-to-frame changes in expression. Training and validation use the ChaLearn LAP dataset of approximately 10,000 annotated videos. Experimental results demonstrate 88.6% overall accuracy, with an average precision of 87.2%, recall of 86.5%, and F1-score of 86.8%, confirming the model’s balanced performance across classes. A minimum loss of 11.3% further underscores effective convergence. The complete pipeline is deployed via Flask, enabling real-time, web-based integration. Beyond academic novelty, this system holds promise for practical applications: in recruitment, it can offer unbiased, rapid personality screening; in mental-health contexts, it may assist clinicians by flagging behavioral cues non-invasively; and in human–computer interaction, adaptive interfaces could personalize responses based on users’ inferred traits. By combining transfer learning with temporal modeling, our approach delivers a scalable, non-invasive tool for automated psychological assessment through visual data, paving the way for ethical, real-time personality analytics in diverse domains.
Pengaruh Budaya Organisasi dan Motivasi Terhadap Loyalitas Karyawan Melalui Kepuasan Karyawan Sebagai Variabel Intervening (Studi Pada Hotel Swiss-Belinn Ska Pekanbaru)
Full text link
Penelitian ini bertujuan untuk mengkaji pengaruh budaya organisasi dan motivasi terhadap loyalitas karyawan dengan kepuasan karyawan sebagai variabel intervening pada karyawan Hotel Swiss-Belinn SKA Pekanbaru. Metode penelitian yang digunakan adalah deskriptif kuantitatif. Populasi penelitian adalah seluruh karyawan Hotel Swiss-Belinn SKA Pekanbaru, dengan jumlah sampel sebanyak 95 responden yang diambil menggunakan teknik sampling jenuh. Analisis data dilakukan menggunakan pemodelan persamaan struktural dengan pendekatan Partial Least Squares (SEM-PLS) untuk menguji hubungan antar variabel. Hasil penelitian menunjukkan bahwa budaya organisasi berpengaruh signifikan terhadap loyalitas karyawan dengan nilai t-statistik sebesar 3.398. Motivasi juga berpengaruh signifikan terhadap loyalitas karyawan dengan nilai t-statistik sebesar 2.394. Selain itu, kepuasan karyawan ditemukan memiliki pengaruh signifikan sebagai variabel intervening dalam hubungan antara budaya organisasi dan loyalitas karyawan, serta antara motivasi dan loyalitas karyawan, dengan nilai t-statistik masing-masing sebesar 2.061 dan 2.498. Temuan ini mengindikasikan bahwa peningkatan budaya organisasi dan motivasi yang baik dapat meningkatkan loyalitas karyawan melalui peningkatan kepuasan kerja mereka. Penelitian ini menyoroti pentingnya budaya organisasi yang kuat dan motivasi yang tinggi dalam menciptakan lingkungan kerja yang memuaskan bagi karyawan, yang pada gilirannya meningkatkan loyalitas mereka terhadap perusahaan. Implikasi praktis dari penelitian ini adalah bahwa manajemen hotel perlu fokus pada pengembangan dan pemeliharaan budaya organisasi yang positif serta memberikan motivasi yang efektif untuk meningkatkan kepuasan dan loyalitas karyawan. Kesimpulan ini memberikan wawasan berharga bagi para praktisi dan akademisi dalam mengelola sumber daya manusia di industri perhotelan yang kompetitif
Peran Orientasi Pelanggan dan Orientasi Pesaing Terhadap Kinerja Pemasaran UMKM Kuliner di Kota Semarang Dengan Inovasi Produk Sebagai Variabel Intervening
Full text linkPenelitian ini memiliki tujuan untuk menganalisa pengaruh orientasi pasar dan orientasi pesaing terhadap kinerja pemasaran, dengan inovasi produk sebagai variabel intervening pada UMKM sektor kuliner di Kota Semarang. pada dalam studi ini metode yang digunakan adalah metode kuantitatif dengan cara melakukan survei, melibatkan 100 responden pelaku UMKM kuliner yang dipilih menjadi sampel. Data dikumpulkan melalui penyebaran kuesioner dan dianalisis menggunakan Partial Least Square (PLS) untuk melakukan pengujian hubungan antar variabel. Hasil studi ini menunjukkan bahwa 71,2% variasi kinerja pemasaran (R-Square = 0,712) dapat dijelaskan oleh model penelitian, yang mencakup orientasi pasar, orientasi pesaing, dan inovasi produk. Temuan ini memperlihatkan bahwasanya strategi pemasaran yang berfokus pada pelanggan dan analisis kompetitor, didukung oleh inovasi produk, secara signifikan berkontribusi terhadap peningkatan kinerja pemasaran UMKM. Penelitian ini diproyeksikan bisa memberi rekomendasi praktis bagi pelaku UMKM kuliner dalam mengoptimalkan strategi pemasaran, serta kontribusi teoritis dalam pengembangan literatur manajemen pemasaran, khususnya mengenai peran orientasi pelanggan dan orientasi pesaing dalam mendorong kinerja bisnis melalui inovasi produk. Implikasi yang didalam temuan ini dapat dijadikan menjadi sebuah acuan bagi pemangku kebijakan dalam merancang program pengembangan UMKM agar lebih efektif