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

doi:10.30656/jsii.v12i2.10917

Authors

Ardian Adam Alfarisyi Telkom University
Mahendra Dwifebri Purbolaksono Telkom University
Alfian Akbar Gozali Telkom University

DOI:

https://doi.org/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

References

[1] Suparna Wijaya, Naufal Setyo, and Waidatin Azizah. Potential analysis and supervision of vat on the utilization of digital contents (case study: Steam platform). Dinasti International Journal of Digital Business Management, 1:342–352, 04 2020.

[2] Andrazˇ Luisa, Jan Hartman, David Nabergoj, Samo Pahor, Marko Rus, Bozhidar Stevanoski, Jure Demsˇar, and Erik Sˇtrumbelj. Predicting the popularity of games on steam, 10 2021.

[3] Jalaluddin Fadhlurrahman, Neng Herawati, Hayyu Aulya, Ira Puspasari, and Nugraha Utama. Sentiment analysis of game reviews on steam using bert, bilstm, and crf. pages 1–6, 10 2023.

[4] Aldira Fazri, Mahendra Dwifebri Purbolaksono, and Widi Astuti. Aspect-based sentiment analysis of beauty product reviews on female daily website using support vector machine and word2vec. pages 230– 235, 07 2024.

[5] Romario Onsu, Daniel Sengkey, and Feisy Kambey. Implementasi bi-lstm dengan ekstraksi fitur word2vec untuk pengembangan analisis sentimen aplikasi identitas kependudukan digital. Jurnal Teknologi Terpadu, 10:46–55, 07 2024.

[6] Maite Jaca-Madariaga, Enara Zarrabeitia, Rosa Rio-Belver, and Marie- Francine Moens. Sentiment analysis model using word2vec, bi-lstm and attention mechanism. 03 2023.

[7] Ruoyu Liu. Exploring the impact of word2vec embeddings across neural network architectures for sentiment analysis. Applied and Computational Engineering, 94:106–111, 11 2024.

[8] Nanjin Li. Logistics demand forecasting and simulation based on support vector machine. Advances in Economics, Management and Political Sciences, 139:143–148, 12 2024.

[9] Zhen Liu. Support Vector Machines, pages 129–140. 01 2025.

[10] Alvi Royyan and Erwin Setiawan. Feature expansion word2vec for sentiment analysis of public policy in twitter. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 6:78–84, 02 2022.

[11] Haili Wang. Word2vec and svm fusion for advanced sentiment analysis on amazon reviews. Highlights in Science, Engineering and Technology, 85:743–749, 03 2024.

[12] Nafiatul Risa, Didik Prasetya, Wahyu Nur Hidayat, Putrinda Maula, I Made Wirawan, and Satria Setiawan. Sentiment analysis of ’kampus merdeka’ on twitter using support vector machine (svm) algorithm. pages 163–168, 11 2024.

[13] Jiale Deng. The data preprocessing technique in machine learning. Science and Technology of Engineering, Chemistry and Environmental Protection, 1, 12 2024.

[14] Botir Elov, Shahlo Khamroeva, and Zilola Khusainova. The pipeline processing of nlp. E3S Web of Conferences, 413, 08 2023.

[15] Tomas Mikolov, Kai Chen, G.s Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. Proceedings of Workshop at ICLR, 2013, 01 2013.

[16] Mariette Awad and Rahul Khanna. Support Vector Machines for Classification, pages 39–66. 04 2015.

[17] Mahfuzul Nissan, James Wagner, and Sharmin Aktar. Database memory forensics: A machine learning approach to reverse-engineer query ac- tivity. Forensic Science International: Digital Investigation, 44:301503, 03 2023.

[18] Ahmad Alshammari. Implementation of model evaluation using confu- sion matrix in python. International Journal of Computer Applications, 186:42–48, 12 2024.

[19] Vimala Balakrishnan and Lloyd-Yemoh Ethel. Stemming and lemma- tization: A comparison of retrieval performances. Lecture Notes on Software Engineering, 2:262–267, 01 2014.

[20] Putra Muhammad, Retno Kusumaningrum, and Adi Wibowo. Senti- ment analysis using word2vec and long short-term memory (lstm) for indonesian hotel reviews. Procedia Computer Science, 179:728–735, 01 2021.

[21] Lailil Muflikhah and Dimas Haryanto. High performance of polynomial kernel at svm algorithm for sentiment analysis. Journal of Information Technology and Computer Science, 3:194, 11 2018.