arXiv subjects

Stéphane Kaufmann

Publications and source records attributed to Stéphane Kaufmann.

4 recordsLinked to original sources

arXiv2026

Games Mapper: Topological Data Analysis of Steam Genres

The video game industry comprises a vast, continuously evolving landscape of themes and genres. For studios and publishers that navigate this competitive market, understanding the structural dynamics and temporal evolution of specific game categories is crucial for identifying viable entry points. In this paper, we introduce Games Mapper, a novel analytical tool based on the Mapper algorithm from topological data analysis. Unlike traditional clustering techniques, Games Mapper captures the continuous topological relationships between datasets over time (or other guiding variables). We extend the standard algorithm with an automated cluster labelling method, ensuring highly interpretable and interactive visualisations of genre evolution. To demonstrate the efficacy of our approach, we present a comprehensive case study on Simulation games released on Steam between 2015 and 2025. Games Mapper autonomously segments the genre into coherent, persistent subgenres, and captures dynamic market shifts. Ultimately, we provide a scalable, generalisable tool for researchers and industrials to unravel complex market structures and track the evolution of the Steam ecosystem.

cs.SI↗

arXiv2025

From Fads to Classics -- Analyzing Video Game Trend Evolutions through Steam Tags

The video game industry deals with a fast-paced, competitive and almost unpredictable market. Trends of genres, settings and modalities change on a perpetual basis, studios are often one big hit or miss away from surviving or perishing, and hitting the pulse of the time has become one of the greatest challenges for industrials, investors and other stakeholders. In this work, we aim to support the understanding of video game trends over time based on data-driven analysis, visualization and interpretation of Steam tag evolutions. We confirm underlying groundwork that trends can be categorized in short-lived fads, contemporary fashions, or stable classics, and derived that the surge of a trend averages at about four years in the realm of video games. After using industrial experts to validate our findings, we deliver visualizations, insights and an open approach of deciphering shifts in video game trends.

cs.HC↗

arXiv2023

Automated clustering of video games into groups with distinctive names

When doing a study on a large number of video games, it may be difficult to cluster them into coherent groups to better study them. In this paper, we introduce a novel algorithm, that takes as input any set of games S that are released on Steam and an integer k, and cluster S into k groups. Each group is then assigned a distinctive name in the form of a Steam tag. We believe our tool to be valuable for gaining deeper insights into the video game market. We show that our algorithm maximises an objective function that we introduce, the naming score, which assesses the quality of a clustering and how distinctive its name is.

cs.HC↗

arXiv2023

Data-Driven Classifications of Video Game Vocabulary

As a novel and fast-changing field, the video game industry does not have a fixed and well-defined vocabulary. In particular, game genres are of interest: No two experts seem to agree on what they are and how they relate to each other. We use the user-generated tags of the video game digital distribution service Steam to better understand how players think about games. We investigate what they consider to be genres, what comes first to their minds when describing a game, and more generally what words do they use and how those words relate to each other. Our method is data-driven as we consider for each game on Steam how many players assigned each tag to it. We introduce a new metric, the priority of a Steam tag, that we find interesting in itself. This allows us to create taxonomies and meronomies of some of the Steam tags. In particular, in addition to providing a list of game genres, we distinguish what tags are essential or not for describing games according to players. Furthermore, we provide a small group of tags that summarise all information contained in the Steam tags.

cs.HC↗