Article Per Year (5 Year)
p-Index From 2021 - 2026
1.532
P-Index
This Author published in this journals
All Journal Science, Technology, and Communication Journal
Okfalisa Okfalisa
Department of Informatics Engineering, UIN Sultan Syarif Kasim Riau, Pekanbaru 28293, Indonesia
Computer Science & IT Electrical & Electronics Engineering Engineering Materials Science & Nanotechnology

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Performance comparison of the Naive Bayes algorithm and the k-NN lexicon approach on Twitter media sentiment analysis Azhar Azhar; Siti Ummi Masruroh; Luh Kesuma Wardhani; Okfalisa Okfalisa
Science, Technology, and Communication Journal Vol. 3 No. 2 (2023): SINTECHCOM Journal (February 2023)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v3i2.229

Abstract

Sentiment analysis or opinion mining is a natural language that processes words to find out opinions, attitudes, or moods about certain things. Word processing in this study related to the process of classification in textual documents, which was classified into three classes, positive, negative, and neutral. Data obtained from social media Twitter were related to netizens' comments as many as 1000 comments. These data were crawled using keywords of the “Pilpres2019” and “Jokowi”. This study compared the performance of the Naive Bayes and k-Nearest Neighbor (k-NN) algorithms with the lexicon approach in classification. The aim of this study was to compare the level of accuracy, precision, and recall of Naive Bayes and the k-NN algorithm with the lexicon approach. From the evaluation, we concluded that the combination of the k-NN algorithm and the lexicon approach could improve accuracy in this sentiment analysis case. Generally, the k-NN algorithm with lexicon approach in which the k value is k = 5 has better performance with a 77% of accuracy level, followed by Naive Bayes with an accuracy of 81% of accuracy level.
Toddler nutritional status identification: Support vector machine (SVM) algorithm adoption Affan Asyraffi; Okfalisa Okfalisa; Fitri Insani; Surya Agustian; Riski Mai Candra
Science, Technology, and Communication Journal Vol. 5 No. 2 (2025): SINTECHCOM Journal (February 2025)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v5i2.282

Abstract

Inadequate nutrition in toddlers can lead to health issues and adversely affect their growth, development, and cognitive capabilities. Consequently, it is essential to assess the nutritional status of toddlers to ascertain their health level. This study seeks to ascertain the nutritional health of toddlers utilizing the support vector machine (SVM) methodology, taking into account body weight (BB), height (TB), age, BB/TB ratio, Z-scores for BB/U, Z-scores for TB/U, and Z-scores for BB/TB. The data of 1458 toddlers were evaluated using the knowledge data discovery methodology. This study effectively categorized toddler nutrition into six classifications including malnutrition, undernutrition, adequate nutrition, overnutrition, risk of overnutrition, and obesity. Utilizing the confusion matrix methodology with an 80% training data to 20% test data ratio yields an accuracy of 89.04%. The SVM method is effectively utilized to ascertain the nutritional condition of toddlers, hence enhancing their growth and development.
Chatbot AI Riau tourism towards society 5.0 success Melia Vivi Ningrum; Sayyidina Anshari Ahmad; M Abyan Belantara; M Dafa Al-Sa’ban; Qistan Alif Santana; Rahmat Alfitri; Okfalisa Okfalisa
Science, Technology, and Communication Journal Vol. 5 No. 1 (2024): SINTECHCOM Journal (October 2024)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v5i1.283

Abstract

Riau Province stands out as one of the most rapidly developing regions in Indonesia, showcasing significant advancements economy, population, and tourism. The strategic positioning of Riau Province along the world's busiest routes, establishes this province as a focal point for diverse activities from multiple nations. Furthermore, the natural resources of Riau Province provide it as a significant business hub by substantial activities. This undoubtedly impacts the cross section both business and tourist visitors from local and international. Unfortunately, it is found that information pertaining to Riau tourism is under-addressed the visitors’ need. Therefore, the chatbot artificial intelligent (AI) is developed to deliver comprehensive information about tourism in Riau, encompassing tourist attractions, culinary, and merchandise destinations. This chatbot is adopted a prototyping approach for software development with natural language processing, employing tools such as Xampp, Visual Studio Code, PHP for programming language, and the Botman for the library. This chatbot is then integrated with a customized website platform utilizing an accessible API. The questions are derived from commonly asked questions on the tourism platform, limited into five tourist attractions, culinary options, or merchandise’s spot. To evaluate, a black-box and user acceptance testing techniques will be employed to verify that the application operates as intended and receives favorable feedback from users. This chatbot grows into the smart and responsive tool tailored to tourism needs in Riau. This tool supports the Society 5.0 that concerns on human centric, technology, and resilience social and community while preserving the cultural elements of Riau’s Malay heritage.
UI/UX design thinking adoption for integrated AI point-of-sale system (Case study: Plastic Poultry Wholesale Store) Okfalisa Okfalisa; Fahruddin Fahruddin; Haris Setiaji; M Farhan Aulia Pratama; Harry Finaldhi; Nur Delifah
Science, Technology, and Communication Journal Vol. 5 No. 3 (2025): SINTECHCOM Journal (June 2025)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v5i3.311

Abstract

The development of artificial intelligence (AI) technology drives the need for a point of sales (POS) system that is not only efficient, but can also provide adaptive information according to the user's sudden wishes. This research implements the design thinking method in designing a user interface (UI/UX) for a smart POS system integrated with conversational AI features. A case study was conducted at a Plastic Poultry Wholesale Store to gain in-depth insights related to field needs and operational challenges faced. The design thinking method was chosen because of its user-centered approach, through the stages of empathize, define, ideate, prototype, and testing, it is hoped that the final results obtained can be aligned with the concrete needs of users, so that the output of the system that has been designed will not be abandoned, but will always be used. In this design, the implementation of conversational AI is used to enhance the user experience through a virtual assistant feature that is able to answer dynamic questions according to the wishes of the user, so that users can freely explore any information in detail related to their overall business performance. The implementation results show that this system not only increases operational efficiency, but also improves user experience through more intuitive interactions when they want to see their business performance. This research contributes to integrating AI technology with a user-centered design approach for smart, responsive, and adaptive POS system solutions.
An IndoBERT-based framework for emotion classification in Indonesian song lyrics Agustar Alfonso; Fitri Insani; Okfalisa Okfalisa; Muhammad Fikry; Fitra Kurnia; Sri Wahyuni
Science, Technology, and Communication Journal Vol. 6 No. 3 (2026): SINTECHCOM Journal (June 2026)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v6i3.372

Abstract

Emotion classification in song lyrics represented a significant research area within natural language processing, yet studies targeting Indonesian-language lyrics remained scarce due to the limited availability of labeled datasets and the absence of domain-specific models. This study developed and evaluated an emotion classification model for Indonesian song lyrics using fine-tuned IndoBERT-base-p2, a transformer-based language model pre-trained on a large Indonesian corpus. A dataset of 1,025 labeled lyric entries was compiled from Kaggle, Genius, and KapanLagi, covering four emotion categories: joy, sadness, fear, and anger. Preprocessing encompassed duplicate removal, case folding, structural marker removal, and non-alphabetic character cleaning. Nine fine-tuning experiments were conducted by systematically varying learning rate and dropout rate, with early stopping applied based on validation loss. The optimal configuration employed a learning rate of 3 × 10-5 and a dropout rate of 0.1, achieving 75.73% accuracy and 75.85% macro-averaged F1-score on the held-out test set. Joy and anger were classified most reliably, attaining F1-scores of 82.76% and 76.47% respectively, while sadness presented the greatest challenge, exhibiting the lowest precision of 64.10% alongside a recall of 80.65%, indicating a systematic tendency of the model to over-predict this class. These findings demonstrated that IndoBERT-base-p2, when fine-tuned with appropriate hyperparameter configuration, served as an effective approach for domain-specific emotion classification in Indonesian song lyrics.
Interpretative comparative analysis of LSTM and random forest for multi-label classification of English Qur’an translation Nur Delifah; Nazruddin Safaat Harahap; Okfalisa Okfalisa; Elvia Budianita
Science, Technology, and Communication Journal Vol. 6 No. 3 (2026): SINTECHCOM Journal (June 2026)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v6i3.373

Abstract

The rapid growth of digital Qur'anic resources has created a need for automated systems capable of accurately categorizing verses by thematic content. The thematic complexity of Qur'anic text, in which a single verse may simultaneously convey multiple moral, spiritual, and social messages, presents a significant challenge for automated classification systems. This study conducts a comparative and explainable evaluation of long short-term memory (LSTM) and random forest (RF) for multi-label classification of English Qur'an translations across six thematic categories: arkanul Islam, iman, amal, human and community relations, akhlak, and history and story. To address severe class imbalance, synthetic minority over-sampling technique (SMOTE) was applied per label, expanding the training set from 4,489 to 19,658 samples. LSTM captured sequential contextual relationships through integer token embeddings, while RF relied on TF-IDF vector representations. Evaluated on 1,248 unseen test verses, RF achieved a higher macro F1-score (0.2748) compared to LSTM (0.2432), while LSTM retained marginally higher accuracy (79.61% vs. 79.55%). Per-label analysis revealed that both models performed best on lexically explicit labels such as arkanul Islam and iman, but consistently failed on abstract categories such as akhlak, where LSTM recorded near-zero recall of 0.61% and RF only 6.10%. This study contributes empirical evidence that TF-IDF-based SMOTE interpolation is more effective for minority-class augmentation than token-sequence interpolation, and demonstrates that macro F1-score is a more appropriate evaluation metric than accuracy for imbalanced multi-label religious text classification.
Robust cryptocurrency price forecasting using a Bayesian-optimized CNN–LSTM hybrid model Abdul Aziz Sulton; Fitri Insani; Okfalisa Okfalisa; Lestari Handayani; Nazruddin Safaat Harahap
Science, Technology, and Communication Journal Vol. 6 No. 3 (2026): SINTECHCOM Journal (June 2026)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v6i3.377

Abstract

The rapid growth of cryptocurrency has caused the price movements of digital assets such as Bitcoin (BTC) and Ethereum (ETH) to become highly volatile and difficult to predict. This study aims to develop a cryptocurrency price prediction model using a hybrid convolutional neural network–long short-term memory (CNN-LSTM) architecture optimized with Bayesian Optimization. The data used in this study consisted of daily historical data for Bitcoin and Ethereum from January 1, 2018, to December 31, 2025, obtained from Yahoo Finance. The research stages included data preprocessing, normalization using Min-Max Scaling, sequence generation using the sliding window method (window sizes of 30, 60, and 90), CNN-LSTM model development, hyperparameter optimization using Bayesian Optimization (30, 50, and 100 trials), and evaluation using regression metrics including MSE, RMSE, MAE, MAPE, and R2. The results showed that the hybrid CNN-LSTM model outperformed the standalone CNN and LSTM models, with RMSE reductions of 27% – 59% for BTC and 18% – 19% for ETH. For Bitcoin data, the best model was obtained using 30 trials with a window size of 30, achieving an RMSE of $2,588.33, MAE of $2,004.23, MAPE of 1.99%, and R2 of 0.9468. Meanwhile, for Ethereum data, the best model was obtained using 50 trials with a window size of 60, achieving an RMSE of $138.56, MAE of $99.75, MAPE of 3.27%, and R2 of 0.9737. These results indicate that the combination of CNN-LSTM and Bayesian Optimization is effective for predicting cryptocurrency prices with non-linear and volatile characteristics.
Data-driven segmentation of sharia-based SMEs digital readiness: Comparing K-means and fuzzy C-means for strategic transformation planning Ananda Vermiansyah; Okfalisa Okfalisa; Rahmad Abdillah; Surya Agustian
Science, Technology, and Communication Journal Vol. 6 No. 3 (2026): SINTECHCOM Journal (June 2026)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v6i3.391

Abstract

Quired to adopt digital technologies while preserving Islamic business principles such as transparency, fairness, trustworthiness, halal integrity, and ethical value creation. However, many sharia-based SMEs still lack clear diagnostic information regarding their digital readinesslevel, making it difficult for policymakers, business associations, and SMEs managers to design targeted digitaltransformation interventions. Prior studies on SMEs digitalisation have largely focused on technology adoption, digital marketing, or general readiness assessment, while limited attention has been given to data-driven segmentation models that can classify sharia-based SMEs into actionable readiness groups. Addressing this gap, this study compares K-means and Fuzzy C-means clustering to identify digital readiness patterns among sharia-based SMEs. The dataset consists of 314 SMES records collected through questionnaires and structured into two main perspectives, includes economic/business readiness and technological/digital readiness. The variables include business activity, transaction capability, management capability, market interaction, macro-environmental readiness, digital culture, digital education, financial resources, and technical infrastructure. Prior to clustering, the data were normalised to ensure comparability across indicators. K-means was used as a hard clustering benchmark because of its computational simplicity and ability to produce clear readiness groups, while Fuzzy C-means was applied as a soft clustering method because SMEs readiness boundaries are often overlapping and gradual rather than strictly separated. The clustering process was designed to generate three readiness categories viz., low, moderate, and high digital readiness. Model evaluation was conducted using silhouette index, Davies–Bouldin index, accuracy, F1-score, computational stability, and principal component analysis-based visualisation. The results show a trade-off between cluster separation quality and classification-oriented performance. Fuzzy C-means achieved a higher silhouette index of 0.1362 and a lower Davies–Bouldin index of 2.6126, indicating better internal cluster quality and stronger ability to represent overlapping readiness characteristics. In contrast, K-means produced higher accuracy of 0.6033 and F1-score of 0.3202, and more clearly formed three practical readiness categories. These findings suggest that Fuzzy C-means is more suitable for exploratory readiness profiling where SMEs may belong partially to more than one readiness stage, whereas K-means is more useful for managerial decision-making requiring crisp classification into low, moderate, and high readiness groups. This study contributes to SMEs digital transformation literature by demonstrating that sharia-based digital readiness should be analysed not only through aggregate scores, but also through segmentation models that reveal heterogeneous readiness patterns. Practically, the proposed comparative clustering framework provides a diagnostic basis for policymakers, Islamic business institutions, and SMEs development agencies to design differentiated digital capability-building programmes.
Decision support system for VARK learning style recommendation using AHP and SAW methods Mutsrin Alim; Yelfi Vitriani; Okfalisa Okfalisa; Lestari Handayani; Muhammad Affandes
Science, Technology, and Communication Journal Vol. 6 No. 3 (2026): SINTECHCOM Journal (June 2026)
Publisher : Lembaga Studi Pendidikan dan Rekayasa Alam Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59190/stc.v6i3.403

Abstract

To establish an objective mechanism for recommending tailored educational approaches, this research focuses on the architectural design of a DSS grounded in the VARK framework, which classifies preferences into visual, auditory, textual, and physical modalities. The operational framework combines AHP and SAW to eliminate subjectivity from the evaluation process. While the extraction of criteria importance factors relied on AHP, utilizing qualitative insights from a psychometrics expert in the field of psychology, the subsequent prioritization of pedagogical options was executed via SAW. Four core dimensions formed the basis of this evaluation, specifically focusing on how individuals perceive stimuli, process information, select instructional materials, and adapt to environmental settings. The initial matrix derivation yielded uniform importance coefficients of 0.25 across all dimensions, supported by a CR of 0 to verify the logical coherence of the expert input. Structurally, the platform was deployed as a responsive web system powered by the Laravel architecture and backed by a MySQL database engine. To confirm computational integrity, the algorithmic outputs generated by the software were audited against traditional manual calculations, resulting in a perfect mathematical alignment. Consequently, the empirical evidence confirms that the engineered DSS offers a precise diagnostic tool, thereby enabling learners to discover optimal educational pathways that correspond directly with their psychological profiles.
Co-Authors Abdul Aziz Sulton Affan Asyraffi Agustar Alfonso Ananda Vermiansyah Azhar Azhar Elvia Budianita Fahruddin Fahruddin Fitra Kurnia Fitri Insani Haris Setiaji Harry Finaldhi Lestari Handayani Luh Kesuma Wardhani M Abyan Belantara M Dafa Al-Sa’ban M Farhan Aulia Pratama Melia Vivi Ningrum Muhammad Affandes Muhammad Fikry Mutsrin Alim Nazruddin Safaat Harahap Nur Delifah Qistan Alif Santana Rahmad Abdillah Rahmat Alfitri Riski Mai Candra Sayyidina Anshari Ahmad Siti Ummi Masruroh Sri Wahyuni Surya Agustian Yelfi Vitriani