Robby Hermansyah
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Analisis Sentimen untuk Evaluasi Reputasi Merek Motor XYZ Berkaitan dengan Isu Rangka Motor di Twitter Menggunakan Pendekatan Machine Learning Ferdian Maulana Akbar; Robby Hermansyah; Sofian Lusa; Dana Indra Sensuse; Nadya Safitri; Damayanti Elisabeth
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 3: Juni 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.938663

Abstract

Motor XYZ mengeluarkan inovasi rangka motor yang diperkenalkan pada tahun 2019. Sekitar Agustus 2023, beredar rumor di media sosial yang menyatakan bahwa rangka tersebut mengalami karat, korosi, dan retak, menyebabkan kekhawatiran di kalangan masyarakat yang tentunya hal ini berpotensi merugikan reputasi merek XYZ. Sasaran utama dari studi ini adalah mengevaluasi pandangan masyarakat di platform Twitter pada Motor XYZ, khususnya pada perbincangan seputar isu rangka motor. Data yang digunakan merupakan data yang diambil teknik crawling dengan periode tweets dari Agustus hingga November 2023. Penelitian ini akan memanfaatkan analisis sentimen menggunakan word cloud, analisis tren dan distribusi, dan pembandingan lima algoritma machine learning, yakni Naïve Bayes, Decision Tree, Support Vector Machine, Logistic Regression, dan Random Forest. Penelitian ini bertujuan untuk mengidentifikasi algoritma dengan performa terbaik untuk mengategorikan tweets dan memberikan rekomendasi kepada Motor XYZ terkait reputasi merek dalam hubungannya dengan isu rangka motor. Hasil penelitian menunjukkan bahwa model klasifikasi sentimen dengan kinerja terbaik setelah hyperparameter tuning adalah Random Forest, dengan F1 score sebesar 0,765. Selain itu, rekomendasi yang dapat diberikan adalah meningkatkan kesadaran tentang pemeriksaan rangka gratis karena telah terbukti berdampak positif pada sentimen masyarakat di Twitter. Perlu ditekankan bahwa dalam penelitian ini tidak ada pertimbangan terhadap proses deployment model machine learning dan pembuatan dashboard. Selain itu, penelitian ini tidak menangani analisis reputasi atau sentimen merek di platform media sosial lain seperti TikTok atau Instagram.   Abstract Motor XYZ introduced an innovative motorcycle frame in 2019. In August 2023, rumors began circulating on social media that these frames were experiencing rust, corrosion, and cracks. This caused public concern and potentially harmed the XYZ brand's reputation. This study aims to evaluate public opinion on Twitter regarding the motorcycle frame issue. Data was collected using crawling techniques from tweets posted between August and November 2023. We used sentiment analysis with word clouds, trend and distribution analysis, and compared five machine learning algorithms: Naïve Bayes, Decision Tree, Support Vector Machine, Logistic Regression, and Random Forest. The goal was to identify the best algorithm for categorizing tweets and provide recommendations to Motor XYZ about their brand reputation concerning the frame issue. Results showed that the Random Forest model, after hyperparameter tuning, had the best performance with an F1 score of 0.765. This study recommend increasing awareness about free frame inspections, as this positively impacted public sentiment on Twitter. Note that this study does not include the deployment process of the machine learning model or dashboard creation, nor does it address brand reputation or sentiment analysis on other social media platforms such as TikTok or Instagram.
A Data-Driven Approach for Game Evaluation Using Latent Dirichlet Allocation Method Based on Players’ Reviews Muhammad Rizky Anditama; Robby Hermansyah; Achmad Nizar Hidayanto
Jurnal Sistem Informasi Vol. 20 No. 2 (2024): Jurnal Sistem Informasi (Journal of Information System)
Publisher : Faculty of Computer Science Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jsi.v20i2.1429

Abstract

Garena is a global game developer and publisher. Garena provides users with access to popular and engaging online games for mobile and PC, developed, curated, and localized for each market. The Battle Royale genre is relatively new, and this research will evaluate Free Fire, one of the games in this genre made by Garena. Analyzing end-user reviews is considered important for evaluating software quality. Researchers need to understand which aspects need to be evaluated based on player reviews on Google Play and how the model's performance is generated using feedback from players who have played Free Fire. In this study, researchers use the Latent Dirichlet Allocation (LDA) method to model topics and generate clusters in discussions for each topic. LDA is a generative probabilistic model of a corpus. This research on topic modeling using Google Play reviews and LDA has identified the topics users are most concerned with. The research shows three main aspects: bugs, graphics and performance, and game rules/punishment policy, as aspects that need to be evaluated based on player reviews on Google Play.