SimSensei Demonstration: A Perceptive Virtual Human Interviewer for Healthcare Applications
Authors: Louis-Philippe Morency, Giota Stratou, David DeVault, Arno Hartholt, Margo Lhommet, Gale Lucas, Fabrizio Morbini, Kallirroi Georgila, Stefan Scherer, Jonathan Gratch, Stacy Marsella, David Traum, Albert Rizzo
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Evaluation With respect to providing an environment where informative behaviors can be elicited and analyzed in relation with distress, relevant work (De Vault et al. 2013; Scherer et al. 2013; Stratou et al. 2014) on the verbal channel and on audio and video modalities respectively, showed that a virtual human interaction is still rich in behaviors that allow for analysis and assessment of distress via fully automatic methods. This was still in the wizard-driven phase of the system, but similar results can be reproduced in the fully automatic system (different stages of the system and the data we collected are described in (Gratch et al. 2014)). Moreover, it was possible to assess the rapport the users felt with our system through self-report questionnaires in each phase. Overall the results were promising; participants reported willingness to disclose, willingness to recommend and general satisfaction with both the wizard-driven and the fully AI version of the system (Lucas et al. 2014). |
| Researcher Affiliation | Academia | Louis-Philippe Morency, Giota Stratou, David De Vault, Arno Hartholt, Margaux Lhommet, Gale Lucas, Fabrizio Morbini, Kallirroi Georgila, Stefan Scherer, Jonathan Gratch, Stacy Marsella, David Traum, Albert Rizzo Institute for Creative Technologies, University of Southern California Los Angeles, California |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include an unambiguous statement about releasing the source code for the described methodology, nor does it provide a direct link to a code repository. |
| Open Datasets | Yes | different stages of the system and the data we collected are described in (Gratch et al. 2014). The Distress Analysis Interview Corpus of human and computer interviews. LREC. |
| Dataset Splits | No | The paper mentions data collection and evaluation but does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, or testing. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions various software components and frameworks (e.g., Multi Sense, PML standard) but does not provide specific version numbers for any ancillary software or dependencies needed to replicate the experiment. |
| Experiment Setup | No | The paper does not contain specific experimental setup details such as concrete hyperparameter values, training configurations, or system-level settings in the main text. |