cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jumanto
Contact Email
jumanto@mail.unnes.ac.id
Phone
+628164243462
Journal Mail Official
sji@mail.unnes.ac.id
Editorial Address
Ruang 114 Gedung D2 Lamtai 1, Jurusan Ilmu Komputer Universitas Negeri Semarang, Indonesia
Location
Kota semarang,
Jawa tengah
INDONESIA
Scientific Journal of Informatics
Published by Universitas Negeri Semarang
ISSN : 24077658     EISSN : 24600040     DOI : https://doi.org/10.15294/sji.vxxix.xxxx
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering
Scientific Journal of Informatics (p-ISSN 2407-7658 | e-ISSN 2460-0040) published by the Department of Computer Science, Universitas Negeri Semarang, a scientific journal of Information Systems and Information Technology which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences. The SJI publishes 4 issues in a calendar year (February, May, August, November).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 131 Documents
 2   3   4   5   6 
Feature Expansion with GloVe and Particle Swarm Optimization for Detecting the Credibility of Information on Social Media X with Long Short-Term Memory (LSTM) Raffly, Famardi Putra Muhammad Raffly; Setiawan, Erwin Budi Setiawan
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.7839

Abstract

Purpose: This research aims to develop a system for detecting the credibility of information on social media X by classifying tweets as credible or non-credible. Additionally, it seeks to improve the accuracy of classification and prediction of information credibility using feature extraction methods, semantic features, feature expansion, and optimization. Methods: The system is built using a deep learning approach with Long Short-Term Memory (LSTM), Term Frequency-Inverse Document Frequency (TF-IDF), Robustly optimized BERT Approach (RoBERTa), Global Vector (GloVe), and Particle Swarm Optimization (PSO). The dataset consists of 54,766 Indonesian tweets from social media X, focusing on the 2024 General Election and using several keywords such as ‘Pemilu 2024’, ‘Pilpres 2024’, ‘anies baswedan’, ‘Prabowo’, ‘#GanjarPranowo’, and ‘#debatCapres’. Result: The results of this study show that the highest accuracy achieved is 89.09% using LSTM with an 80:20 data split, baseline unigram, RoBERTa, Top1 corpus IndoNews, and PSO of the LSTM model’s hyperparameters, resulting in a highly significant statistical improvement of 0.96% over the baseline model. Novelty: This research contributes to information credibility classification research using RoBERTa to add semantic features and GloVe to expand features by utilizing a built corpus and finding similar words to connect with these expanded features. Additionally, PSO is applied to find the optimal hyperparameters, thereby improving the performance and accuracy of the LSTM classification model.
Comparison of Extremely Randomized Survival Trees and Random Survival Forests: A Simulation Study Zaenal, Mohamad Solehudin; Fitrianto, Anwar; Wijayanto, Hari
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.8464

Abstract

Abstract. Purpose: This simulation study investigates the Extremely Randomized Survival Trees (EST) model, a machine learning technique expected to handle survival analysis, particularly in large survival datasets, effectively. The study compares the performance of the EST model with that of the Random Survival Forest (RSF) model, focusing on the C-index value to determine which model performs better. Methods: The analysis begins with the generation of 540 simulated datasets, created by combining three levels of sample sizes, two levels of censoring proportions, three types of hazard functions, and 30 repetitions for each scenario. The simulation data were split into 80% training and 20% testing data. The training data were used to build the EST and RSF models, while the test data were used to evaluate their performance. The model with the highest C-index value was deemed the best performer, as a higher C-index indicates superior model performance. Result: The results indicate that the sample size, type of hazard function, and the method used influence that model performance. The EST model significantly outperformed the RSF model when the sample size was large, though no significant difference was observed when the sample size was small or medium. Additionally, the EST model consistently demonstrated faster computation times across all simulation scenarios. Novelty: This study provides a pioneering exploration into applying decision tree algorithms, specifically EST and RSF, in survival analysis. While these methods have been extensively studied in regression and classification contexts, their application in survival analysis remains relatively unexplored.
Effect of Business Digitalization and Social Media on MSME Performance with Digital Competence as a Mediating Variable Titin; Sutrisno; Mahmudah, Henny; Muhtarom, Abid; Syamsuri
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.9942

Abstract

Abstract. Purpose: The advancement of digital technology has fundamentally transformed the business landscape. Business digitalization and social media utilization have emerged as key drivers in SME strategies to enhance performance. This research aims to assess the effect of business digitalization and social media utilization on SME performance and to examine the role of digital competence as a mediator in this relationship. Method: This study employed a quantitative approach utilizing SEM-PLS methodology to explore the interrelationships among relevant variables. The study was conducted on 51 SMEs in Lamongan Regency, Indonesia, using an online questionnaire as the data collection tool. Result: The study findings revealed that business digitalization, social media utilization, and digital competence have a significant and positive effect on SME performance in Lamongan Regency. Moreover, digital competence is a significant mediator between business digitalization, social media utilization, and SME performance. These findings underscore that digital competence enables SMEs to optimize the benefits of business digitalization and social media, thereby enhancing operational efficiency, expanding market reach, and adapting to market changes swiftly and effectively. Novelty: In particular, the implementation of digital technology in production processes, integration of digital systems in business management, social media utilization for marketing and customer interaction, and the development of digital competence are key factors in enhancing operational efficiency, reducing costs, increasing sales and revenue, and improving customer satisfaction and loyalty among MSMEs.
Information System for Managing Village-Owned Enterprises (BUMDes) in Bogoharjo Village with DevOps Method Buchori, Achmad; Muthoharoh, Nurul Afifah; Wijayanto
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.6627

Abstract

Purpose: The purpose of this research is to build a Bogoharjo Village-Owned Enterprises (BUMDes) Business Unit Management Information System to facilitate BUMDes managers in managing business units and providing available services to the community online. Methods: The method used in this research is the DevOps method with the stages of plan, code, build, test, release, deploy, operate, and monitor. System design uses UML (Unifed Modeling Language), namely flowchart, use case diagram, activity diagram, class diagram, and sequence diagram. System development using the Laravel framework. Results: The results showed that expert validation with an average percentage by content expert validation of 89% and media expert validation of 84% so that the BUMDes Management Information System (Village-Owned Enterprises) in Bogoharjo Village with the DevOps Method was very feasible to use. While the results of the practicality trial using 25 respondents produced an average percentage of 89% with a very practical category. Thus, the BUMDes Management Information System (Village-Owned Enterprises) in Bogoharjo Village with the DevOps Method is very practical to use. Novelty: The novelty of this research is used to assist BUMDes managers in managing data or providing information related to the BUMDes itself. In addition, BUMDes management becomes more organized and structured so that services to the community become more effective and well managed.
Community Acceptance of SIKESAL: An UTAUT Model Approach in E-Government Services in Jambi City Bulya, Bulya; Ulung Pribadi
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.7511

Abstract

Purpose: This research examines the factors influencing public acceptance of e-government services, particularly the Sikesal system in Jambi City. The urgency of this research lies in its potential to improve the quality of public services, increase community engagement, and support digital transformation goals in Jambi City. This study contributes to understanding how local communities perceive and utilize e-government services, providing insights to improve service design and Using the Unified Theory of Acceptance and Use of Technology (UTAUT) model, we evaluated variables including Performance Expectancy, Effort Expectancy, Social Influence, and Facilitating Conditions. The study utilized a quantitative approach, collecting data through questionnaires distributed to 100 respondents, selected using the Slovin formula. Result: Results indicate that Effort Expectancy significantly impacts the use of e-government services (T value of 18.339, P value of 0.000), highlighting the importance of user-friendliness. However, performance expectancy, social influence, and facilitating conditions did not significantly impact. Novelty: The novelty of this study lies in its localized examination of e-government acceptance, providing insights for targeted improvements in service design and implementation.
Analysis of User Experience of the CapCut Application in Generation Z for Social Media Content Using the User Experience Questionnaire Method Wulan, Damar; Syaifullah; Saputra, Eki; Rahmawita, Medyantiwi; Marsal, Arif
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.7543

Abstract

Purpose: In the midst of these dynamics of change, research, development and application of technology continues to be the main focus in efforts to achieve progress and efficiency in various sectors of life. Generation Z has been the primary architect of cultural and behavioral change on social media. One of the most prominent characteristics of Generation Z is their desire to create "viral" content on social media. Content created using CapCut often uses interesting video and audio effects, such as progress effects, dry effects, music effects, and so on. This application has various features that make it easier for users to create video content, such as video effects, audio and animation. This shows that generation Z tends to use the CapCut application to create and edit video content that they share on social media. This research was conducted based on a phenomenon that has recently occurred, where many generations Z want to create content on social media using the CapCut application and also from several previous studies that have been conducted which are still lacking in understanding CapCup user satisfaction as a medium for creating content for Generation Z. and from several interviews the author conducted with CapCut application users. Method: This research uses the user experience questionnaire (UEQ) method with six (6) variables, namely attractiveness, efficiency, clarity, dependability, stimulation and novelty. Dr. Martin Schrepp developed a special tool that can be used to analyze UEQ questionnaire results, namely the UEQ Data Analysis Tool. The UEQ Data Analysis Tool is in the form of an Excel application which can be obtained by downloading it directly from the official https://www.ueq-online.org/ website This study employs a quantitative research strategy. This study does not know the exact number of the population to be studied. So, the sample size was calculated using the Lemeshow formula, a survey was conducted on 96 users of the Capcut application. Result: Based on the results of the discussion regarding user experience, specifically Generation Z, in the CapCut Application using the User Experience Questionnaire (UEQ) method, conclusions can be drawn from the 6 variables in the UEQ used, the 6 variables obtained positive evaluation values, namely the Attractiveness (mean 1.177), Perspicuity variables. (mean 1.109), Efficiency (mean 1.109), Dependability (mean 1.159), Stimulation (mean 1.151) and Novelty (mean 0.763) with the highest evaluation value on the Attractiveness variable. 2. Based on the benchmark results, the values obtained for the Attractiveness variable were 1.18, Perspicuity 1.11, Efficiency 1.11, Dependability 1.16, Stimulation 1.15, and Novelty 0.76. Each variable gets an Above Average value (above the average). However, there is still potential for improvement to achieve standards of perfection desired. Users provided invaluable feedback and suggestions, highlighting the need for improvement. Novelty: This research provides 2 recommendations based on the results of evaluations using UEQ, which are expected to help in improving and improving the quality of the CapCut Application in the future.
Hybrid Deep Learning with GloVe and Genetic Algorithm for Sentiment Analysis on X: 2024 Election Fitria, Mahrunissa Azmima Fitria; Setiawan, Erwin Budi
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.8467

Abstract

Purpose: This research analyzes sentiment on the 2024 Indonesian Presidential Election using  data from X, employing a hybrid CNN-GRU model optimized with a Genetic Algorithm (GA) to improve accuracy and efficiency. It also explores GloVe feature expansion for enhanced sentiment classification, aiming for deeper insights into public opinion through advanced deep learning and optimization techniques. Methods: This research employs a deep learning approach that integrates Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) models, Term Frequency-Inverse Document Frequency (TF-IDF), Global Vectors (GloVe), and GA. The dataset comprises  62,955 Indonesian tweets focusing on the 2024 General Election using various keywords. Result: The results indicated that the Genetic Algorithm significantly improved model accuracy. The CNN-GRU + GA model achieved 84.72% accuracy for the Top 10 ranking, a 1.94% increase from the base model. In comparison, the GRU-CNN + GA model achieved 84.69% accuracy for the Top 5 ranking, a 2.76% increase from the base model, demonstrating enhanced performance with GA across configurations. Novelty: This research uses a hybrid CNN-GRU model to introduce a novel sentiment analysis approach for the 2024 Indonesian Presidential Election. The model enhances accuracy by combining CNN's spatial feature extraction with GRU's temporal context capture and GloVe's word semantics. Genetic Algorithm optimization further refines performance. Comprehensive pre-processing ensures high-quality data, and focusing on election-specific keywords adds relevance. This study advances sentiment analysis through its innovative hybrid model, feature expansion, and optimization techniques.
Sort Filter Skyline in Movie Recommendation Based on Individual Preferences: Performance and Time Complexity Analysis Fadhilah, Alvi Nur; Cahyanto, Triawan Adi; Saifudin, Ilham
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.8474

Abstract

Purpose: This study seeks to deliver accurate, customized movie recommendations using the Sort Filter Skyline (SFS) algorithm. The approach considers factors like budget, box office earnings, popularity, runtime, and audience ratings to align closely with each user's specific preferences. Methods: The Sort Filter Skyline (SFS) algorithm is employed, designed to identify and recommend items different from others within the dataset. Initially, the data undergoes preparation through pre-processing before being analyzed to compute entropy using the entropy formula. Before carrying out the dominance test, the SFS algorithm organizes the data based on entropy values. Result: In this research, 176 skyline objects were identified from a dataset containing 4,803 movies, including well-known titles like "Avatar" and "Titanic." The Skyline Filter Sort (SFS) algorithm pinpointed these objects within 4 seconds. Additionally, evaluation results using synthetic data, as depicted in the data visualization, revealed that the number of attributes increased from 1 to 7. The dataset size grew, and the execution time also rose—from 18 seconds to 170 minutes. Despite this increase, the algorithm demonstrated efficient performance with optimized processing times. Novelty: This study showcases the successful application of the SFS algorithm for generating personalized movie recommendations while tackling the difficulty of aligning viewer preferences with the extensive selection of films available. The findings offer important insights into enhancing recommendation systems by implementing algorithms efficiently and managing execution time complexity, contributing fresh perspectives to the field.
Behavioral Intention and Adoption of Clinical Informatics Tools: A Study in Regional Public Municipality Clinics Mdunge, Eric Njabulo; Ezeji , Ijeoma Noella; Evans , Neil
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.8794

Abstract

Purpose: The healthcare sector is vital for addressing public health emergencies and improving overall health outcomes. This paper aims to explore the factors that influence the adoption of clinical informatics by healthcare professionals in public clinics within a KwaZulu Natal municipality in South Africa. The paper adopted the Unified Theory of Acceptance and Use of Technology (UTAUT) to understand determinants of behavioral intention to use, and actual usage of these clinical informatics tools by the sampled healthcare professionals. Methods: The paper adopted a mixed-methods approach to answer the research questions, both primary quantitative and secondary qualitative data was collected and analysed. Surveys and interviews were conducted with 67 sampled healthcare professionals including doctors, nurses, administrative staff and 10 managers to obtain the primary quantitative data and secondary qualitative data respectively. SPSS was used to analyse the quantitative data and thematic content analysis was used to analyse for the qualitative data. Result: Results indicate that the constructs of UTAUT positively influence healthcare workers’ intention to use and use of clinical informatics tools, these include in the order of their influence, performance expectancy, effort expectancy, social influence and facilitating conditions. While clinical informatics tools are available and frequently used by healthcare workers, significant challenges are mentioned to impede their effective adoption. These challenges include insufficient hardware, lack of awareness and training about ICT applications, and limited access to data network infrastructure such as Wi-Fi hotspots and routers. Novelty: The novelty of this research lies in its comprehensive analysis of both the behavioral and infrastructural factors affecting the adoption of clinical informatics in a specific municipal context. Conducted in a municipality that serves both rural and urban communities, this study provides practical recommendations to overcome identified adoption barriers. The findings contribute to developing strategies for the adoption and provision of clinical informatics tools to improve healthcare delivery in South Africa.
Combining Multiple Text Representations for Improved Automatic Evaluation of Indonesian Essay Answers Wibowo, Moh Edi; Rokhman, Nur; Sihabudin, Agus
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.9440

Abstract

multiple-choices, regarding students’ learning achievement. When the number of students in a class is huge, however, examinations using essay questions become hard to conduct and take a long evaluation time. Automatic essay evaluation has, therefore, become a potential approach in this situation. Various methods have been proposed, however, optimal solutions for such evaluation in the Indonesian language are less known. Furthermore, with the rapid development of machine learning approaches, in particular deep learning approaches, the investigation of such optimal solutions becomes more necessary. Method: To address the aforementioned issue, this study proposed the investigation of text representation approaches for optimal automatic evaluation of Indonesian essay answers. The investigation compared pre-trained word embedding methods such as Word2vec, GloVe, FastText, and RoBERTa, as well as compared text encoding methods such as long short-term memories (LSTMs) and transformers. LSTMs are able to capture temporal semantics by employing state variables, while transformers are able to capture long-term dependency between parts of their input sequences. Additionally, we investigated classification-based and similarity-based training to build text encoders. We expected that these training approaches allowed encoders to extract different views of information. We compared classification results produced by different text encoders and combinations of text encoders. Result: We evaluated various text representation approaches using the UKARA dataset. Our experiments showed that the FastText word embedding method outperformed the Word2vec, GloVe, and RoBERTa methods. The FastText method achieved an F1-score of 75.43% on validation sets, while the Word2vec, GloVe, and RoBERTa methods achieved F1-scores of 69.56%, 74.53%, and 72.87%, respectively. In addition, the experiments showed that combinations of text encoders outperformed individual encoders. The combination of the LSTM encoder, the transformer encoder, and the TF-IDF encoder obtained an F1-score of 77.22% in the best case, which is better than the best F1-scores of the individual LSTM encoders (75.35%), the best combination of transformer encoders (71.49%), and the individual TF-IDF encoder (76.69%). We observed that LSTM encoders produced better performance when they were built using classification-based training. Meanwhile, the transformer encoders obtained better performance when built using similarity-based training. Novelty: The novelty proposed in this research is the optimal combination of text encoders specifically constructed for the evaluation of essay answers in the Indonesian language. Our experiments showed that the combination of three encoders - namely the LSTM encoder built using classification-based training, the transformer encoder built using classification-based and similarity-based training, and the TF-IDF encoder - obtained the best classification performance.

Page 4 of 14 | Total Record : 131

 2   3   4   5   6 

Filter by Year

2024 2025


Reset
Filter By Issues
All Issue Vol. 12 No. 4: November 2025 Vol. 12 No. 3: August 2025 Vol. 12 No. 2: May 2025 Vol. 12 No. 1: February 2025 Vol. 11 No. 4: November 2024 Vol. 11 No. 3: August 2024 Vol. 11 No. 2: May 2024