Visualizing and understanding players' behavior in video games
Bibliographic record
Abstract
As video games become more popular, there is an urge for procedures that can support the analysis and understanding of players' behaviors within game environments. Such data would inform game and level designers of game design issues that should be fixed or improved upon. By logging user-initiated events in video games, analysts have exhaustive information regarding players' actions within games. However, visualizing such data is a challenging task due to the amount of data one has to deal with; the necessity of a deep understanding of the game and players' possible actions within the game plus a deep understanding of questions one wants to answer; the computation that has to be done on the data; and the limitations and/or complexities of current analysis tools. In this paper, we present a new visualization system that allows analysts to build visualization and interact with telemetry data, to identify patterns and identify game design issues efficiently. Besides the system itself, we propose a new approach to visualize players' behavior that has not been explored so far. For example, instead of using heat maps to visualize a single metric (e.g. deaths), our system allows analysts to superimpose and visualize a series of actions players take in the game. This is especially important when one should understand cause and effect within the game. We present examples of the visualizations using an RPG game, Dragon Age Origins (BioWare/EA, 2009). It should be noted that the system is currently under development and testing with analysts working at BioWare.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".