Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
LOL โ Laugh Out Loud
Authors: Florian Pecune, Beatrice Biancardi, Yu Ding, Catherine Pelachaud, Maurizio Mancini, Giovanna Varni, Antonio Camurri, Gualtiero Volpe
AAAI 2015 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In our demo, Lo L, a user interacts with a virtual agent able to copy and to adapt its laughing and expressive behaviors on-the-๏ฌy. |
| Researcher Affiliation | Academia | Florian Pecune, Beatrice Biancardi, Yu Ding, Catherine Pelachaud CNRS LTCI, Telecom Paris Tech 37-39, rue Dareau, Paris, France Maurizio Mancini, Giovanna Varni, Antonio Camurri, Gualtiero Volpe DIBRIS Universit a degli Studi di Genova Viale Causa 13, Genova, Italia |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described in this paper. |
| Open Datasets | No | The paper mentions using 'script files containing time markers' and 'funny audio stimuli' but does not provide concrete access information for a publicly available or open dataset. |
| Dataset Splits | No | The paper describes a demo and does not provide specific dataset split information needed to reproduce data partitioning. |
| Hardware Specification | Yes | Body features are computed on the user s silhouette extracted from the BW depth map... captured by a Kinect sensor. |
| Software Dependencies | No | The paper mentions 'Eyes Web XMI' and 'Greta agent platform' but does not provide specific ancillary software details with version numbers. |
| Experiment Setup | Yes | For the demo, we take two parameters into account to drive the agent s behavior: (1) user s body leaning and (2) user s laughter intensity. The user s body leaning is directly mapped to the agent s body leaning: if the user leans forward, the agent leans forward as well. User s laughter intensity has a global in๏ฌuence on the agent s body movements. A high intensity augments the amplitude of the agent s movements, whereas a small intensity reduces this amplitude. |