Loading…

Prov-DIFF: Play traces analysis through provenance differences

•Prov-DIFF compares provenance graphs from multiple sessions to determine the differences and understand the underlying reasons for the outcomes.•Our diff allows the designer, developers, and players to detect sections of the graph that differ from others.•Our approach proposes changes that can be m...

Full description

Saved in:
Bibliographic Details
Published in:Entertainment computing 2025-01, Vol.52, p.100777, Article 100777
Main Authors: Costa Kohwalter, Troy, Gresta Paulino Murta, Leonardo, Walter Gonzalez Clua, Esteban
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Prov-DIFF compares provenance graphs from multiple sessions to determine the differences and understand the underlying reasons for the outcomes.•Our diff allows the designer, developers, and players to detect sections of the graph that differ from others.•Our approach proposes changes that can be made in the player’s actions to improve his results in a future session.•Evaluated through an experimental study regarding a projectile motion simulation. A game session comprises a series of user decisions, inputs, and the execution of a strategy to reach specific goals. Tracking generated data of a game session is important for game analytics for developers and players. Game session data can be used for reproducibility, analysis of game traces, understanding player behavior, and improving the outcome in future sessions by learning from mistakes. However, game telemetry can rapidly lead to large amounts of data that can overwhelm the analyst’s ability to analyze it, and it can be difficult to identify the reasons that might have caused a player to lose in that session. This paper proposes a provenance-based automatic debugging approach for game analytics. It identifies possible reasons and discrepancies that might have led a player to lose by contrasting their performance with other players. Our approach also proposes possible insights on how to improve the player’s performance to reach the goal. We integrated our solution into the existing provenance visualization tool Prov Viewer. We provided an experimental study to demonstrate that our approach can identify probable causes that led the player to lose and propose changes to make it work in the next execution.
ISSN:1875-9521
1875-953X
DOI:10.1016/j.entcom.2024.100777