MétaCan
Menu
Back to cohort
Record W4205398686 · doi:10.1109/cog52621.2021.9619099

Predicting Beliefs from NPC Dialogues

2021· article· en· W4205398686 on OpenAlex
Jason T. Bowey, Julian Frommel, Brandon Piller, Regan L. Mandryk

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venue2021 IEEE Conference on Games (CoG) · 2021
Typearticle
Languageen
FieldSocial Sciences
TopicDigital Games and Media
Canadian institutionsUniversity of Saskatchewan
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsHarmNarrativeComputer scienceEmbeddingWork (physics)Human–computer interactionPsychologySocial psychologyArtificial intelligenceEngineeringLinguistics

Abstract

fetched live from OpenAlex

Game designers and developers benefit from gathering data from players; however, interrupting play with questionnaires can harm experience. Previous work has suggested that embedding questionnaires into games, such as through dialogue choices when interacting with non-player characters (NPCs) can help, but there is no evidence that dialogue choices can model the real-world beliefs of players. In this study we demonstrate two methods of successfully predicting responses to validated scales of sexist beliefs from NPC dialogues that do not differ in their resulting narrative engagement. Our findings open opportunities for better tailoring games and game experiences by modeling players through their in-game interactions.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.933
Threshold uncertainty score0.998

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0030.001

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.

Opus teacher head0.060
GPT teacher head0.298
Teacher spread0.238 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it