Modeling player engagement is a key challenge in games. However, the gameplay signatures of engaged players can be highly context-sensitive, varying based on where the game is used or what population of players is using it. Traditionally, models of player engagement are investigated in a particular context, and it is unclear how effectively these models generalize to other settings and populations. In this work, we investigate a Bayesian hierarchical linear model for multi-task learning to devise a model of player engagement from a pair of datasets that were gathered in two complementary contexts: a Classroom Study with middle school students and a Laboratory Study with undergraduate students. Both groups of players used similar versions of Crystal Island, an educational interactive narrative game for science learning. Results indicate that the Bayesian hierarchical model outperforms both pooled and context-specific models in cross-validation measures of predicting player motivation from in-game behaviors, particularly for the smaller Classroom Study group. Further, we find that the posterior distributions of model parameters indicate that the coefficient for a measure of gameplay performance significantly differs between groups. Drawing upon their capacity to share information across groups, hierarchical Bayesian methods provide an effective approach for modeling player engagement with data from similar, but different, contexts.
more »
« less
"I Want To See How Smart This AI Really Is": Player Mental Model Development of an Adversarial AI Player
Understanding players' mental models are crucial for game designers who wish to successfully integrate player-AI interactions into their game. However, game designers face the difficult challenge of anticipating how players model these AI agents during gameplay and how they may change their mental models with experience. In this work, we conduct a qualitative study to examine how a pair of players develop mental models of an adversarial AI player during gameplay in the multiplayer drawing game iNNk. We conducted ten gameplay sessions in which two players (n = 20, 10 pairs) worked together to defeat an AI player. As a result of our analysis, we uncovered two dominant dimensions that describe players' mental model development (i.e., focus and style). The first dimension describes the focus of development which refers to what players pay attention to for the development of their mental model (i.e., top-down vs. bottom-up focus). The second dimension describes the differences in the style of development, which refers to how players integrate new information into their mental model (i.e., systematic vs. reactive style). In our preliminary framework, we further note how players process a change when a discrepancy occurs, which we observed occur through comparisons (i.e., compare to other systems, compare to gameplay, compare to self). We offer these results as a preliminary framework for player mental model development to help game designers anticipate how different players may model adversarial AI players during gameplay.
more »
« less
- NSF-PAR ID:
- 10381871
- Date Published:
- Journal Name:
- Proceedings of the ACM on Human-Computer Interaction
- Volume:
- 6
- Issue:
- CHI PLAY
- ISSN:
- 2573-0142
- Page Range / eLocation ID:
- 1 to 26
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In recent years, various mechanisms have been proposed to optimize players’ emotional experience. In this paper, we focus on suspense, one of the key emotions in gameplay. Most previous research on suspense management in games focused on narratives. Instead, we propose a new computational model of Suspense for Non-Narrative Gameplay (SNNG). SNNG is built around a Player Suspense Model (PSM) with three key factors: hope, fear, and uncertainty. These three factors are modeled as three sensors that can be triggered by particular game objects (e.g., NPCs) and game mechanics (e.g., health). A player’s feeling of suspense can be adjusted by altering the level of hope, fear, and uncertainty. Therefore, an SNNG-enhanced game engine could manage a player’s level of suspense by adding or removing game objects, diverting NPCs, adjusting game mechanics, and giving or withholding information. We tested our model by integrating SNNG into a Pacman game. Our preliminary experiment with nine subjects was encouraging.more » « less
-
Integrating fabrication activities into existing video games provides opportunities for players to construct objects from their gameplay and bring the digital content into the physical world. In our prior work, we outlined a framework and developed a toolkit for integrating fabrication activities within existing digital games. Insights from our prior study highlighted the challenge of aligning fabrication mechanics with the existing game mechanics in order to strengthen the player aesthetics. In this paper, we address this challenge and build on our prior work by adding fabrication components to the Mechanics-Dynamics-Aesthetics (MDA) framework. We use this f-MDA framework to analyze the 47 fabrication events from the prior study. We list the new player-object aesthetics that emerge from integrating the existing game mechanics with fabrication mechanics. We identify connections between these emergent player-object aesthetics and the existing game mechanics. We discuss how designers can use this mapping to identify potential game mechanics for integrating with fabrication activities.more » « less
-
In multiplayer collaborative games, players need to coordinate their actions and synchronize their efforts effectively to succeed as a team; thus, individual differences can impact teamwork and gameplay. This article investigates the effects of cognitive styles on teams engaged in collaborative gaming activities. Fifty-four individuals took part in a mixed-methods user study; they were classified as field-dependent (FD) or independent (FI) based on a field-dependent–independent (FD-I) cognitive-style-elicitation instrument. Three groups of teams were formed, based on the cognitive style of each team member: FD-FD, FD-FI, and FI-FI. We examined collaborative gameplay in terms of team performance, cognitive load, communication, and player experience. The analysis revealed that FD-I cognitive style affected the performance and mental load of teams. We expect the findings to provide useful insights on understanding how cognitive styles influence collaborative gameplay.more » « less
-
more » « less
Devising models that reliably recognize player goals is a key challenge in creating player-adaptive games. Player goal recognition is the task of automatically recognizing the intent of a player from a sequence of observed player actions in a game environment. In open-world digital games, players often undertake suboptimal and varied sequences of actions to achieve goals, and the high degree of freedom afforded to players makes it challenging to identify sequential patterns that lead toward specific goals. To address these issues, we present a player goal recognition framework that utilizes a fine-tuned T5 language model, which incorporates our novel attention mechanism called Temporal Contrary Attention (TCA). The T5 language model enables the framework to exploit correlations between observations through non-sequential self-attention within input sequences, while TCA enables the framework to learn to eliminate goal hypotheses by considering counterevidence within a temporal window. We evaluate our approach using game trace data collected from 144 players' interactions with an open-world educational game. Specifically, we investigate the predictive capacity of our approach to recognize player goals as well as player plans represented as abstract actions. Results show that our approach outperforms non-linguistic machine learning approaches as well as T5 without TCA. We discuss the implications of these findings for the design and development of player goal recognition models to create player-adaptive games.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3549482
