Human versus machine: Analyzing video game user reviews for plot and narrative

Abstract

Video game users have shown strong interests in having subject metadata to find games. However, creating and maintaining subject metadata is costly and difficult. This study explores the utility of an automated approach for generating subject metadata for video games, focusing on plot and narrative. By comparing two methods to analyze the reviews—qualitative analysis conducted by a human researcher vs. automated text analysis using topic modeling—the researchers investigate if an automated method can generate subject terms that are comparable to the ones generated by qualitative analysis. Findings suggest that even with a smaller set of sample dataset, qualitative analysis could create a better set of terms than automated text analysis. However, terms generated from the automated text analysis indicate that its capability to retrieve themes of the video game may be useful in future libraries.

AI-Powered Game Design: Experts Employing ChatGPT in the Game Design Process

“…AI-powered platforms, such as GPT-3, have also been used to generate game content (Sobieszek & Price, 2022;Vartinen et al, 2022;Shakeri at al., 2021). These tools have the potential to free up game developers' time and creativity by taking care of repetitive or time-consuming tasks, enabling them to focus on other aspects of game development (Delarosa et al, 2021, Larsson et al, 2022Charity et al, 2020;Li & Xing, 2021;Zagal & Tomuru, 2013;Busurkina et al, 2020;Eberhard et al, 2018;Cho et al, 2020). By enabling faster iteration, these tools have increased game design efficiency and creativity.…”

Individuals responsible for video games: an exploration of cataloging practice, user need and authorship theory

“…Future research should address approaches to finding and selecting accurate information from publicly available user-generated information, such as user reviews and crowdsourced databases. Some of the recent studies utilized text-mining methods to identify subject elements of video games like plot/narrative (Cho et al. , 2020) and suggest the possibility of more autonomous identification and application of information.…”

“…The strategies users employ to explore otherwise unknown resources, in turn, impact the provision of metadata in information resources. Common categorizations for games in online resources include classification by gameplay mechanics, narrative content and visual style, to name just a few (Cho et al ., 2018, 2020; Lee et al ., 2017a, 2018). Gamers also use what resemble more traditional metadata categories, e.g.…”

Authorship Metadata for Video Games: "Collaborator", "Creator", or "Auteur"?

“…Video game users may want to find games with particular visuals created by their favorite illustrators, or with voice actors whose work they enjoy. Seeking to meet these diverse user needs, several studies have created organizational schema for video games based on subject relationship information, such as gameplay mechanics, frame of reference, narrative content, setting, and visual style (Cho et al 2018;Cho et al 2020;Lee et al 2017). However, a uthorship or creatorship in the realm of video games is not always easy to discern, or even conceptualiz e, which may have contributed to the de facto standard practice of recording game studios' names in the author field.…”