Sistem Deteksi Reputasi Akun Seller Pada Steam Community Menggunakan Metode Klasifikasi Support Vector Machine

Nalom Aholiab Sinaga, Alexander Setiawan, Agustinus Noertjahyana


Playing games is an activity that is often done by many people from various ages, some just fill their free time, some make the game a job or a place to make money. The online gaming industry is currently an industry with a large value, which is $21.1 million in 2021. The Steam Community is an online game platform that provides nearly 30000 games. In this platform, you can not only play games but can make transactions with fellow Steam Community users. The transactions made include selling games, ingame accessories, steam wallets and artwork. The problem faced is, payment transactions are carried out outside the Steam platform itself, on the other hand Steam users do not know each other yet, so the seller's account reputation needs to be checked. The checks carried out are through analyzing the sentiment on the comments of the account in question. Analyzing these comments is done by using the Support Vector Machine method to classify the purpose and sentiment of the comments. The results of this research will be presented in the form of a website where users of this website-based application will enter SteamID into the system, and the system will perform sentiment analysis on comments, then the system displays the results of the analysis in the form of data presentations, in the form of the number of comments based on existing sentiments. And the system will also display all comments on the profile along with the predictions for their comments. Based on research that has been carried out using the Support Vector Machine method, the model with the best accuracy is 91% for classification of comments purposes, and 86% for sentiment classification. Based on a survey of this application, 76% of respondents claimed to be helped by this application, and 66% of respondents were willing to recommend this application to their friends.


Sentiment Analysis; Steam Community; Support Vector Machine

Full Text:



Amrizal, V. (2018). Penerapan Metode Term Frequency

Inverse Document Frequency (Tf-Idf) Dan Cosine Similarity

Pada Sistem Temu Kembali Informasi Untuk Mengetahui

Syarah Hadits Berbasis Web (Studi Kasus: Hadits Shahih


(2), 149-164. doi: 10.15408/jti.v11i2.8623

Clement, J. (2021). Topic: Online gaming. Retrieved 6

January 2022, from

Darmawan, L. (2017). Stemming Word dalam Carik Bot.

Retrieved 9 January 2022, from

Ilmawan, L., & Mude, M. (2020). Perbandingan Metode

Klasifikasi Support Vector Machine dan Naïve Bayes untuk

Analisis Sentimen pada Ulasan Tekstual di Google Play Store.

ILKOM Jurnal Ilmiah, 12(2), 154-161. doi:


Liu, B. (2012). Sentiment Analysis and Opinion Mining.

Morgan & Claypool Publishers.

Moore, C., & Wang, D. (2018). Support vector machine

(machine learning). Radiopaedia.Org. doi: 10.53347/rid61710

Murphy, A., & Moore, C. (2019). Confusion matrix.

Radiopaedia.Org. doi: 10.53347/rid-68080

Nasrudin, A. (2022). Apa itu Reputasi?. Retrieved 7 July

, from

Salam, A., Zeniarja, J., & Khasanah, R. (2018). Analisis

Sentimen Data Komentar Sosial Media Facebook Dengan KNearest Neighbor (Studi Kasus Pada Akun Jasa Ekspedisi

Barang J&T Ekspress Indonesia). In SINTAK 2018.

Semarang. Retrieved from

Saputra, I., & Rosiyadi, D. (2019).

Perbandingan Kinerja Algoritma K-Nearest Neighbor, Naïve

Bayes Classifier dan Support Vector Machine dalam

Klasifikasi Tingkah Laku Bully pada Aplikasi Whatsapp..

Faktor Exacta, 12(2), 101. doi:


The World's Largest API Hub | RapidAPI. (2022). Retrieved

July 2022, from


  • There are currently no refbacks.

Jurnal telah terindeks oleh :