Aspect Based Sentiment Analysis to Explore Gameplay Topics in Game Software Evolution (Robocraft Study Case)

DOI

10.2991/978-94-6239-828-3_24How to use a DOI?

Keywords

aspect-based sentiment analysis; topic modeling; BERTopic; BERT; player reviews; game software evolution

Abstract

The digital game industry has experienced rapid growth driven by increasing demand for digital entertainment, giving rise to online distribution platforms such as Steam that provide review features enabling players to share their gaming experiences. Player reviews accumulated in large volumes represent a strategic source of information for developers seeking to understand community perceptions toward each game update. This study analyzes player review sentiment in Robocraft toward gameplay mechanism aspects — encompassing Building Mechanics, Player Progression, and PVP System — across major patch updates from July 2014 to November 2019. Employing a two-stage pipeline combining BERTopic for topic exploration and BERT-based Aspect-Based Sentiment Analysis (ABSA) for sentiment classification, the study processed over 15,000 unique reviews collected via the Steam API. Results identify 2016 as a permanent turning point in community sentiment, wherein the progression system overhaul during the CPU Update + Epic Loot period triggered a negative sentiment dominance that never recovered through the game’s server shutdown in 2025. These findings indicate that Robocraft’s decline was driven more by monetization decisions perceived as exploitative rather than a failure of its core creative concept, which remained consistently appreciated throughout the game’s development.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Gabriela Edith Petra Febriandhini
AU  - Nanang Yudi Setiawan
AU  - Fajar Pradana
PY  - 2026
DA  - 2026/11/04
TI  - Aspect Based Sentiment Analysis to Explore Gameplay Topics in Game Software Evolution (Robocraft Study Case)
BT  - Proceedings of the 2026 11th International Conference on Sustainable Information Engineering and Technology (SIET 2026)
PB  - Atlantis Press
SP  - 270
EP  - 280
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6239-828-3_24
DO  - 10.2991/978-94-6239-828-3_24
ID  - Febriandhini2026
ER  -