IJID (International Journal on Informatics for Development)

Uncovering Insights in Spotify User Reviews with Optimized Support Vector Machine (SVM)

2025-01-15T09:34:58+07:00

The rapid growth of user-generated reviews on platforms like Spotify necessitates efficient analytical techniques to extract valuable insights. This study employs a Support Vector Machine algorithm, optimized using Forward Selection, Backwards Elimination, Optimized Selection, Bagging, and AdaBoost, to effectively classify user reviews. A dataset of approximately 10,000 Spotify reviews was compiled from diverse online sources, ensuring a representative sample. The analysis reveals sentiment patterns across positive, negative, and neutral categories, with positive reviews dominates the landscape. These patterns help highlight Spotify’s strengths while identifying areas for improvement. However, the SVM algorithm faces challenges in classifying minority classes, particularly negative sentiments, due to class imbalance. To address this, advanced optimization techniques are utilized to enhance classification precision and recall. Preprocessing steps, including data cleansing, tokenization, stemming, and stopword removal, refine the dataset, while TF-IDF converts text into numerical features for effective feature selection. The results show that the Optimized Selection method achieves the highest accuracy of 84.5%, outperforming other approaches. This research contributes significantly to developing balanced sentiment analysis models. Future studies may explore deep learning techniques to further improve classification accuracy and mitigate current limitations in data representation.

The Impact of Algorithms on Decision-Making in Daily Life: A Polling Study of Technology Users

2025-02-17T12:26:17+07:00

Algorithms have become an integral part of everyday life, particularly in entertainment, shopping, and navigation. This study examines how algorithms influence individual decision-making. Data were collected through an online poll involving 200 respondents, selected using a statistical sampling method. The results indicate that 55% of respondents perceive algorithms as having a significant influence on their decisions, while 28% report a moderate impact. A confidence interval analysis (95%) has been included to ensure statistical accuracy. The study highlights the importance of digital literacy in mitigating algorithmic bias and suggests future research on how socio-cultural factors shape algorithmic perceptions. This research contributes to understanding the extent of algorithmic influence on daily decision-making and raises user awareness of technology’s impact. The implications include the importance of digital literacy to mitigate dependency and bias in algorithm usage and the potential to develop more transparent and ethical algorithmic systems. Future research could explore the relationship between users' awareness of algorithms and their behaviors in various contexts and evaluate ways to enhance public understanding of how algorithms function in the evolving digital ecosystem.

Implementation and Performance Analysis of PVD Method in Concealing Encrypted Data on Images

2025-02-05T08:52:40+07:00

This research aims to secure text data by combining steganography and cryptography. The Pixel Value Differencing (PVD) method allows for higher data insertion capacity with minimal distortion, thereby increasing resistance to steganalysis. However, the PVD steganography method is vulnerable to variation in image areas and to the accuracy of Pixel Difference Histogram (PDH) analysis. In addition, this method is susceptible to statistical tools such as the chi-square and RS, which can be used to analyze the distribution of pixel value differences, allowing data to be detected. To address the limitations of the PVD method, we employed a cryptographic technique called XOR-VLSB, which combines XOR as the primary encryption method, Vigenère Cipher for key generation, and Least Significant Bit (LSB) for key embedding. The results showed that the fully encrypted data could be recovered and had good image quality, as indicated by the metric results, which included a low MSE value, a PSNR above 35 dB, and an SSIM value close to 1. In this study, the process of encrypting text data still uses a simple encryption algorithm, namely XOR. Future research may involve replacing cryptographic algorithms with AES, which offers stronger protection and better resistance to advanced security threats.

Towards Fair and Efficient Timetabling: A Genetic Algorithm Model Integrating Lecturer Day-Off Requests

2025-04-25T07:39:09+07:00

This study tackles the complex challenge of lecture timetabling by incorporating lecturer day-off preferences, a crucial constraint often neglected in traditional scheduling methods. Given the NP-hard nature of the problem and the need for scalable solutions, a Genetic Algorithm (GA) was employed with a population size of 10, a crossover probability of 0.70, a mutation probability of 0.20, and a maximum generation of 10000. The proposed GA-based method, implemented using PHP and MySQL, is applied to a real-world scenario involving 25 courses, 22 lecturers, and six classrooms over a 5-day weekly schedule at the Faculty of Education and Teacher Training for the Even Semester of the 2023/2024 Academic Year. Experimental results, validated through the Mann-Whitney test, show that incorporating lecturer preferences enhances scheduling flexibility without significantly increasing computational time. Comparative analysis with Simulated Annealing and Tabu Search demonstrates the competitive performance of the GA-based method in optimizing lecture schedules. This study provides a practical solution for educational institutions seeking to improve their timetabling processes.

LDA Topic Modeling Analysis of Public Discourse on Indonesia’s Free Nutritious Meals Program (MBG)

2025-05-27T12:33:55+07:00

This study investigates public discourse on Indonesia's Free Nutritious Meals (Makan Bergizi Gratis/MBG) program through Latent Dirichlet Allocation (LDA) topic modeling of YouTube comments. Filling a research gap on online public opinion regarding the MBG policy, this study identifies dominant themes and discursive patterns in public perception. A three-topic model, validated through coherence score evaluation and pyLDAvis visualization, reveals key topics: concerns over food prices and distribution, perceived benefits for children and society, and emotionally and politically driven reactions. The findings provide valuable insights into public opinion, while also highlighting challenges in processing Indonesian-language text, such as informal language and noisy data. This study contributes to understanding public perceptions of social policies in digital environments and recommends future research directions, including improved text preprocessing and alternative topic modeling approaches. By shedding light on online public discourse, this research informs policymakers and stakeholders about the effectiveness and potential areas for improvement in the MBG program.