Dramatis: A Computational Model of Suspense
Authors: Brian O'Neill, Mark Riedl
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We report on three evaluations of Dramatis, including a comparison of Dramatis output to the suspense reported by human readers, as well as ablative tests of Dramatis components. |
| Researcher Affiliation | Academia | Brian O'Neill Western New England University brian.oneill@wne.edu Mark O. Riedl Georgia Institute of Technology riedl@cc.gatech.edu |
| Pseudocode | No | The paper describes the computational model's processes in narrative text but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The operators, scripts, and all versions of the stories used in these evaluations are available in (O Neill 2013). |
| Open Datasets | Yes | The operators, scripts, and all versions of the stories used in these evaluations are available in (O Neill 2013). |
| Dataset Splits | No | The paper describes experiments comparing its model to human ratings and ablative tests, but it does not specify any training, validation, or test dataset splits for its internal model development or evaluation. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory, or cloud resources) used to run the experiments. |
| Software Dependencies | No | The paper mentions using a 'modified version of the Heuristic Search Planner (HSP)' but does not provide specific version numbers for any software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | Thirty-two participants were recruited to read natural language versions of the stories described above. All participants read the story pairs in the same order (Casino Royale, Rear Window, Harry Potter), but we controlled for reading order within-pairs (original vs. alternate versions). After reading each individual story, participants answered the question, How suspenseful was this story? on a 7-point ordinal Likert scale. After each pair of stories, participants indicated which version of the story was more suspenseful... |