Claim Missing Document
Check
Articles

WORD EMBEDDING ANALYSIS IN SENTIMENT ANALYSIS USING MACHINE LEARNING: A CASE STUDY OF STEAM RPG GAME REVIEWS Ardian Adam Alfarisyi; Mahendra Dwifebri Purbolaksono; Alfian Akbar Gozali
Jurnal Sistem Informasi Vol. 12 No. 2 (2025)
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jsii.v12i2.10917

Abstract

User reviews on gaming platforms such as Steam have become a crucial source of information for potential players before making purchasing decisions. Due to the varied nature of user opinions, sentiment analysis is essential for processing and interpreting these reviews. This study investigates the application of sentiment analysis to RPG game reviews on Steam, aiming to assist users by summarizing reviews through sentiment results and providing insights into the general perception of a game. To achieve this, the study applies sentiment analysis using Word2Vec and Support Vector Machine (SVM). It focuses on evaluating the impact of lemmatization during preprocessing and analyzing the performance of Word2Vec in sentiment classification. Word2Vec transforms review text into vector representations that capture semantic relationships, enhancing the model’s ability to understand context. Meanwhile, SVM is chosen as the classifier for its effectiveness in distinguishing between positive and negative reviews and handling high-dimensional data. The system developed uses Word2Vec with 300-dimensional vectors combined with an SVM Polynomial classifier, resulting in the best performance among the tested models. The final model achieves a macro-average F1-score of 88.6%, indicating a strong capability in accurately classifying sentiments in user reviews. These results highlight the potential of combining word embedding and machine learning techniques for analyzing sentiment in gaming platforms.   Keywords: sentiment analysis, Word2Vec, SVM, Steam, RPG
Menjelajah Desa Wisata dengan Teknologi VR: Inovasi Dosen Telkom University di Cibiru Wetan Maulid, Hariandi; Prawita, Fat'hah Noor; Gozali, Alfian Akbar
IHSAN : JURNAL PENGABDIAN MASYARAKAT Vol 7, No 2 (2025): Ihsan: Jurnal Pengabdian Masyarakat (Oktober)
Publisher : University of Muhammadiyah Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30596/ihsan.v7i2.22727

Abstract

Desa wisata kini menjadi tujuan favorit wisatawan yang ingin menikmati pengalaman autentik dan unik di luar destinasi wisata konvensional. Namun, banyak desa wisata menghadapi tantangan dalam menarik perhatian wisatawan, terutama mereka yang berada di luar area geografis desa tersebut. Pandemi global yang baru saja berlalu juga mengubah pola perjalanan wisata, mendorong adopsi teknologi digital, termasuk teknologi realitas virtual (Virtual Reality/VR) dan realitas tertambah (Augmented Reality/AR), untuk memperkenalkan destinasi wisata secara interaktif. Tim dosen dari Fakultas Ilmu Terapan, Telkom University, yaitu Hariandi Maulid, Dr.Eng. Alfian Akbar Gozali, S.T., M.T., dan Fat’hah Noor Prawita, telah meluncurkan program pengabdian masyarakat yang berjudul Implementasi Aplikasi VR untuk Pariwisata untuk Masyarakat Desa Cibiru Wetan. Program ini dirancang untuk memanfaatkan teknologi VR guna meningkatkan daya tarik Desa Cibiru Wetan sebagai destinasi wisata.
One Data Indonesia Policy Adoption for Telkom University Data Warehouse Framework Gozali, Alfian Akbar; Romadhony, Ade; A, Subaveerapandiyan
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 9 No 2 (2023): July
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v9i2.3473

Abstract

The Indonesian government has implemented a data warehouse named One Data (Satu Data) Indonesia (ODI) to support its operations since 2019. However, the implementation of this concept in universities has been limited, with only a few universities adopting it. Telkom University is one of the few universities in Indonesia that has already taken steps to implement ODI at the university level. The adoption of ODI at Telkom University is known as the One Data Telkom University (ODTU) project. This project aims to create a platform for universities to share data and collaborate more effectively. This paper thoroughly examines the implementation of the ODI policy and data warehouse framework at Telkom University, focusing on the ODTU data warehouse design and architecture. This paper discusses the implementation of ODTU into several applications, including the One Data Portal, One Data Dashboard, and One Data Market. Moreover, it identifies the challenges encountered during the implementation process, such as data integration, data privacy and security, standardized data models, and the promotion of a shared vision among stakeholders with varying levels of data literacy. Our analysis results demonstrate the effectiveness of the ODTU framework in improving data management practices at Telkom University. The customer satisfaction index (CSI) shows that across key reliability, assurance, and responsiveness measures, Telkom University experienced average score improvements of 3-6% after implementing ODTU. This study contributes to the existing literature on ODI policy adoption in the context of higher education institutions, providing insights for institutions seeking to improve their data management practices.
Hybrid Multi-Objective Metaheuristic Machine Learning for Optimizing Pandemic Growth Prediction Adiwijaya, Adiwijaya; Pane, Syafrial Fachri; Sulistiyo, Mahmud Dwi; Gozali, Alfian Akbar
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.981

Abstract

Pandemic and epidemic events underscore the challenges of balancing health protection, economic resilience, and mobility sustainability. Addressing these multidimensional trade-offs requires adaptive and data-driven decision-support tools. This study proposes a hybrid framework that integrates machine learning with multi-objective optimization to support evidence-based policymaking in outbreak scenarios. Six key indicators—confirmed cases, disease-related mortality, recovery count, exchange rate, stock index, and workplace mobility—were predicted using eight regression models. Among these, the XGBoost Regressor consistently achieved the highest predictive accuracy, outperforming other approaches in capturing complex temporal and socioeconomic dynamics. To enhance interpretability, we developed SHAPPI, a novel method that combines Shapley Additive Explanations (SHAP) with Permutation Importance (PI). SHAPPI generates stable and meaningful feature rankings, with immunization coverage and transit station activity identified as the most influential factors in all domains. These importance scores were subsequently embedded into the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to construct Pareto-optimal solutions. The optimization results demonstrate transparent trade-offs among health outcomes, economic fluctuations, and mobility changes, allowing policymakers to systematically evaluate competing priorities and design balanced intervention strategies. The findings confirm that the proposed framework successfully balances predictive performance, interpretability, and optimization, while providing a practical decision-support tool for epidemic management. Its generalizable design allows adaptation to diverse geographic and epidemiological contexts. In general, this research highlights the potential of hybrid machine learning and metaheuristic approaches to improve preparedness and policymaking in future health and socioeconomic crises.
Power Station Engine Failure Early Warning System Using Thermal Camera Gozali, Alfian Akbar
Jurnal Penelitian Pendidikan IPA Vol 9 No 8 (2023): August
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v9i8.4598

Abstract

Power station engines are critical infrastructure components that require constant monitoring to prevent failures and ensure an uninterrupted power supply. This paper proposes a failure early warning system based on a thermal camera using a computer vision approach. The system uses a thermal camera to generate thermal images in a video format, which is then processed by an automated fire detection engine and temperature detection engine. The results of these two subsystems are then used as input for an anomaly detection engine, which predicts the likelihood of engine failure. Based on the results of the experiments, it can be concluded that the YOLOv7 model outperforms Faster R-CNN in detecting fires, achieving a higher mAP score on the one-class dataset. The proposed temperature and anomaly detection system also accurately detected temperature levels and anomalies in thermal images. Furthermore, in the failure time prediction experiment, the Holt-Winters additive method with additive errors, additive trend, and additive seasonality model was identified as the best fit among the models evaluated. In contrast, the Decision Tree model showed good performance and a short training time, making it a good choice for applications where training time is critical. These results highlight the importance of selecting the most suitable method for a given application. Moreover, it demonstrates the effectiveness of different models and approaches for engine failure early warning systems in a power station using a thermal camera.
ByTani (Platform Jual Beli Hasil Pertanian Online Berbasis Website) Pangestu, Citra; Akbar Gozali, Alfian
eProceedings of Applied Science Vol. 9 No. 1 (2023): Februari 2023
Publisher : eProceedings of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstract—Indonesia is one of the second largest agricultural countries in the world after Brazil. Most of Indonesia's population works in agriculture. This sector accounts for 13.28% of gross domestic product in 2021. Indonesia's very strategic location, starting from the geographical side, causes Indonesia to be in a tropical area which has two seasons. These factors make Indonesia very suitable for the agricultural sector. However, the distribution process of rice yields in Indonesia has many obstacles, including the habit of local farmers selling through collectors so that the profit margin obtained is relatively small. In this final project, a solution called ByTani is proposed (a website-based online agricultural trading platform), a trading platform for agricultural products that will connect farmers with buyers directly so that farmers' profits can increase. Based on a survey conducted by the author on March 1, 2022, to farmers in the West Java area, data obtained that 66.7% of farmers have privately owned rice fields. Of all the farmers interviewed, all sold their produce to local collectors in their area. The sale of crops to collectors creates another problem, namely that farmers become dependent on collectors and have narrow sales targets. Meanwhile, 66.7% of farmers stated that the purchase price from collectors was relatively cheap compared to the total costs incurred during the process of planting rice to harvesting. Based on the test results, 68.5% of farmers agree with the problem that the collector's purchase price is quite low. Based on the solutions offered, 73.3% of farmers agree that the ByTani application as an intermediary for selling farmers' crops can help increase the profit of selling rice.Keywords— Indonesia, agriculture, farmers, collectors, application
Mamarikan : Web Platform Penjualan Hasil Ikan Laut Dan Olahannya Yusuf Basqara, Muhammad; Akbar Gozali, Alfian
eProceedings of Applied Science Vol. 9 No. 1 (2023): Februari 2023
Publisher : eProceedings of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstrak — Indonesia merupakan negara maritim yang memiliki luas wilayah laut sekitar 3,25 juta Km2 dan 2,55 juta km2 zona ekonomi eksklusif sehingga Indonesia merupakan negara dengan kekayaan laut melimpah. Berdasarkan penelitian dari LIPI bahwa Indonesia memiliki potensi kekayaan laut mencapai Rp. 1.700 Triliun, hal ini setara dengan 93% APBN Indonesia pada tahun 2018. Hal ini, berbanding terbalik dengan kondisi ekonomi masyarakat yang berprofesi sebagai nelayan karena pandemi mengakibatkan dampak ekonomi terhadap nelayan. Data menunjukkan bahwa ratarata penurunan harga komoditas di beberapa daerah menurun hingga 10% diakibatkan hambatan pengiriman komoditas, permintaan yang menurun dan lainnya. Dalam proyek akhir ini, tim mengusulkan solusi berjudul mamarikan yaitu sebuah platform jual beli berbagai jenis hasil laut baik yang mentah atau sudah diolah secara online berbasis website. Berdasarkan survey yang dilakukan oleh tim pada agustus 2021 bahwa para nelayan menjual hasil tangkap mereka kepada pengepul yang kemudian para pengepul besar akan menjual hasil yang dia beli kepada pengepul kecil dilanjutkan ke pedagang di pasar lalu ke konsumen. Hal ini menyebabkan harga bahan pokok yang mahal tetapi harga beli yang murah. Oleh karena itu, mamarikan hadir untuk meningkatkan kesejahteraan nelayan dengan mengurangi alur distribusi yang panjang.Kata kunci — nelayan, indonesia, hasil laut, website, pengepul, kelautan
Mamarikan : Web Platform Penjualan Hasil Ikan Laut Dan Olahannya Abduh Husaini Batubara, Muhammad; Akbar Gozali, Alfian
eProceedings of Applied Science Vol. 9 No. 1 (2023): Februari 2023
Publisher : eProceedings of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstrak — Indonesia merupakan negara maritim yang memiliki luas wilayah laut sekitar 3,25 juta Km2 dan 2,55 juta km2 zona ekonomi eksklusif sehingga Indonesia merupakan negara dengan kekayaan laut melimpah. Berdasarkan penelitian dari LIPI bahwa Indonesia memiliki potensi kekayaan laut mencapai Rp. 1.700 Triliun, hal ini setara dengan 93% APBN Indonesia pada tahun 2018. Hal ini, berbanding terbalik dengan kondisi ekonomi masyarakat yang berprofesi sebagai nelayan karena pandemi mengakibatkan dampak ekonomi terhadap nelayan. Data menunjukkan bahwa ratarata penurunan harga komoditas di beberapa daerah menurun hingga 10% diakibatkan hambatan pengiriman komoditas, permintaan yang menurun dan lainnya. Dalam proyek akhir ini, tim mengusulkan solusi berjudul mamarikan yaitu sebuah platform jual beli berbagai jenis hasil laut baik yang mentah atau sudah diolah secara online berbasis website. Berdasarkan survey yang dilakukan oleh tim pada agustus 2021 bahwa para nelayan menjual hasil tangkap mereka kepada pengepul yang kemudian para pengepul besar akan menjual hasil yang dia beli kepada pengepul kecil dilanjutkan ke pedagang di pasar lalu ke konsumen. Hal ini menyebabkan harga bahan pokok yang mahal tetapi harga beli yang murah. Oleh karena itu, mamarikan hadir untuk meningkatkan kesejahteraan nelayan dengan mengurangi alur distribusi yang panjang.Kata kunci — Nelayan, Indonesia, Hasil Laut, Website, Pengepul, Kelautan
Recarbon: Aplikasi Edukasi Jejak Karbon Berbasis Flutter Pangestuaji Widodo, Akhdan; Akbar Gozali, Alfian
eProceedings of Applied Science Vol. 9 No. 1 (2023): Februari 2023
Publisher : eProceedings of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstrak - Berdasarkan data dari Global Carbon Atlas pada tahun 2019, menunjukan bahwa Indonesia menempati urutan ke-8 penyumbang emisi gas rumah kaca tertinggi di dunia dengan total emisi sebesar 618 Metric Ton CO2. Untuk menangani permasalahan ini, pemerintah menerbitkan mata pelajaran Pendidikan Lingkungan Hidup yang diatur dalam UU no. 32 Tahun 2009 tentang perlindungan dan pengelolaan lingkungan hidup terutama pasal 65 ayat 2 bahwa salah satu hak masyarakat adalah mendapatkan pendidikan lingkungan hidup. Namun, solusi dari pemerintah tersebut kurang efektif dikarenakan kurangnya pemahaman masyarakat dan pendidik terhadap permasalahan pendidikan lingkungan dan kurikulum pendidikan lingkungan yang belum memadai dan kurang aplikatif. Oleh karena itu, kami mengangkat permasalahan jejak karbon dan menawarkan solusi teknologi pendidikan yaitu ReCarbon. ReCarbon, merupakan aplikasi berbasis Flutter yang bertujuan untuk membantu masyarakat dalam meningkatkan pengetahuan tentang jejak karbon dan pola hidup ramah lingkungan melalui pendekatan edukasi serta agar pendidikan lingkungan dapat dilakukan lebih aplikatif dan menyenangkan. Hasil dari pengujian kepada 61 target pengguna terkait keefektifan, kebergunaan dan, kepuasan tampilan aplikasi menghasilkan ratarata presentase sebesaar 88,99% yang artinya target pengguna sangat setuju bahwa ReCarbon dapat memenuhi tujuannya.Kata Kunci - jejak karbon, perubahan iklim, pendidikan, lingkungan, aplikasi, flutter
ByTani (Platform Jual Beli Hasil Pertanian Online Berbasis Website) Yudhono, Efwandha; Gozali, Alfian Akbar
eProceedings of Applied Science Vol. 9 No. 1 (2023): Februari 2023
Publisher : eProceedings of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstract—Indonesia is one of the second largest agricultural countries in the world after Brazil. Most of Indonesia's population works in agriculture. This sector accounts for 13.28% of gross domestic product in 2021. Indonesia's very strategic location, starting from the geographical side, causes Indonesia to be in a tropical area which has two seasons. These factors make Indonesia very suitable for the agricultural sector. However, the distribution process of rice yields in Indonesia has many obstacles, including the habit of local farmers selling through collectors so that the profit margin obtained is relatively small. In this final project, a solution called ByTani is proposed (a website-based online agricultural trading platform), a trading platform for agricultural products that will connect farmers with buyers directly so that farmers' profits can increase. Based on a survey conducted by the author on March 1, 2022, to farmers in the West Java area, data obtained that 66.7% of farmers have privately owned rice fields. Of all the farmers interviewed, all sold their produce to local collectors in their area. The sale of crops to collectors creates another problem, namely that farmers become dependent on collectors and have narrow sales targets. Meanwhile, 66.7% of farmers stated that the purchase price from collectors was relatively cheap compared to the total costs incurred during the process of planting rice to harvesting. Based on the test results, 68.5% of farmers agree with the problem that the collector's purchase price is quite low. Based on the solutions offered, 73.3% of farmers agree that the ByTani application as an intermediary for selling farmers' crops can help increase the profit of selling rice.Keywords— indonesia, agriculture, farmers, collectors, application