Seeing and hearing what has not been said: a multimodal client behavior classifier in Motivational Interviewing with interpretable fusion
| dc.rights.license | open | en_US |
| hal.structure.identifier | Institut des Systèmes Intelligents et de Robotique [ISIR] | |
| dc.contributor.author | GALLAND, Lucie | |
| hal.structure.identifier | Institut des Systèmes Intelligents et de Robotique [ISIR] | |
| dc.contributor.author | PELACHAUD, Catherine | |
| hal.structure.identifier | Sommeil, Addiction et Neuropsychiatrie [Bordeaux] [SANPSY] | |
| dc.contributor.author | PECUNE, Florian | |
| dc.date.accessioned | 2025-01-03T08:21:48Z | |
| dc.date.available | 2025-01-03T08:21:48Z | |
| dc.date.conference | 2024-05-28 | |
| dc.identifier.uri | oai:crossref.org:10.1109/fg59268.2024.10581979 | |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/204128 | |
| dc.description.abstractEn | Motivational Interviewing (MI) is an approach to therapy that emphasizes collaboration and encourages behavioral change. To evaluate the quality of an MI conversation, client utterances can be classified using the MISC code as either change talk, sustain talk, or follow/neutral talk. The proportion of change talk in a MI conversation is positively correlated with therapy outcomes, making accurate classification of client utterances essential. In this paper, we present a classifier that accurately distinguishes between the three MISC classes (change talk, sustain talk, and follow/neutral talk) leveraging multimodal features such as text, prosody, facial expressivity, and body expressivity. To train our model, we perform annotations on the publicly available AnnoMI dataset to collect multimodal information, including text, audio, facial expressivity, and body expressivity. Furthermore, we identify the most important modalities in the decision-making process, providing valuable insights into the interplay of different modalities during a MI conversation. | |
| dc.description.sponsorship | Entrainement d'aptitudes sociales affectives personnalisées et adaptées avec des agents culturels virtuels - ANR-19-JSTS-0001 | en_US |
| dc.description.sponsorship | adaPtAtion de l'iNtelligence artificielle pOur l'inteRActiOn homme-MAchine - ANR-20-IADJ-0008 | en_US |
| dc.language.iso | EN | en_US |
| dc.publisher | IEEE | en_US |
| dc.source | crossref | |
| dc.subject.en | Change talk | |
| dc.subject.en | Multimodality | |
| dc.subject.en | Interpretable | |
| dc.title.en | Seeing and hearing what has not been said: a multimodal client behavior classifier in Motivational Interviewing with interpretable fusion | |
| dc.type | Communication dans un congrès | en_US |
| dc.identifier.doi | 10.1109/fg59268.2024.10581979 | en_US |
| dc.subject.hal | Informatique [cs]/Interface homme-machine [cs.HC] | en_US |
| bordeaux.page | 1-9 | en_US |
| bordeaux.hal.laboratories | SANPSY (Sommeil, Addiction, Neuropsychiatrie) - UMR 6033 | en_US |
| bordeaux.institution | Université de Bordeaux | en_US |
| bordeaux.institution | CNRS | en_US |
| bordeaux.conference.title | 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG) | en_US |
| bordeaux.country | tr | en_US |
| bordeaux.conference.city | Istanbul | en_US |
| bordeaux.import.source | dissemin | |
| hal.proceedings | oui | en_US |
| hal.conference.organizer | IEEE | en_US |
| hal.conference.end | 2024-05-31 | |
| hal.popular | non | en_US |
| hal.audience | Internationale | en_US |
| hal.export | false | |
| workflow.import.source | dissemin | |
| dc.rights.cc | Pas de Licence CC | en_US |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.spage=1-9&rft.epage=1-9&rft.au=GALLAND,%20Lucie&PELACHAUD,%20Catherine&PECUNE,%20Florian&rft.genre=unknown |
