A Non-intrusive Approach for 2D Platform Game Design Analysis Based on Provenance Data Extracted from Game Streaming

Jacob, Lidson Barbosa; Kohwalter, Troy C.; Machado, Alex Fernandes da Veiga; Clua, Esteban; Oliveira, Daniel de

doi:10.1109/sbgames.2014.33

Cited by 11 publications

(2 citation statements)

References 9 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge this work represents the only general approach for training automatic models for deriving player experience from gameplay video. Jacob et al (2014) represents the most related example of prior work. The researchers made use of a game-dependent image recognition method to collect logs of actions from gameplay video of Super Mario World.…”

Section: Related Workmentioning

confidence: 99%

Player Experience Extraction from Gameplay Video

Luo

Guzdial

Liao

et al. 2018

AIIDE

View full text Add to dashboard Cite

The ability to extract the sequence of game events for a given player's play-through has traditionally required access to the game's engine or source code. This serves as a barrier to researchers, developers, and hobbyists who might otherwise benefit from these game logs. In this paper we present two approaches to derive game logs from game video via convolutional neural networks and transfer learning. We evaluate the approaches in a Super Mario Bros. clone, Mega Man and Skyrim. Our results demonstrate our approach outperforms random forest and other transfer baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

Player Experience Extraction from Gameplay Video

Luo

Guzdial

Liao

et al. 2018

AIIDE

View full text Add to dashboard Cite

show abstract

“…The provenance support in SDM allowed for a broader range of analysis by using collected provenance information to generate a provenance graph [15]. In another work, Lidson et al [16] extracted provenance information using a non-intrusive technique through image processing mechanisms. In a more recent work, Kohwalter et al [17] also demonstrated the benefits of using the PinG approach during game analysis of serious games, helping students to understand the underlying reasons for an outcome.…”

Section: Introductionmentioning

confidence: 99%

Capturing Game Telemetry with Provenance

Kohwalter

Murta

Clua

2017

2017 16th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames)

View full text Add to dashboard Cite

The outcome of a game session is derived from a series of events, decisions, and interactions that are made during the game. Many processes and techniques have been developed by the game industry in order to understand this outcome. A successful method is game analytics, which aims at understanding the player behavior patterns to improve game quality and enhance the player experience. However, the current methods for analytics are not sufficient to capture the underlying cause-and-effect influences that shape the outcome of a game session. These relationships allow developers and designers to better identify possible mistakes in the gameplay design or to fine-tune their games. In a recent work, Kohwalter et al. introduced a conceptual framework based on provenance to capture these relationships and manually instantiated such framework in some games. In this paper, we propose a concrete component for capturing provenance data and the causeand-effect relationships among game objects, and for automatically building the correspondent provenance graph. This provenance data allows a more powerful support for the visual game analytics. We implemented our component in the Unity game engine and show two case studies over open-source games.

show abstract