@inproceedings{maman-2021-acii,  
 author={Maman, Lucien and Chetouani, Mohamed and Likforman-Sulem, Laurence and Varni, Giovanna},  
 booktitle={2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII)},   
 title={Using Valence Emotion to Predict Group Cohesion’s Dynamics: Top-down and Bottom-up Approaches},   
 year={2021}, 
 pages={1-8},
 abstract={Cohesion is an affective group phenomenon. It has received a lot of attention from scholars both in Social Sciences and in Affective Computing that showed that cohesion and emotion influence each other, highlighting the need to jointly analyze them. This study presents 2 deep neural network architectures grounded on multitask learning to jointly predict cohesion and emotion. Inspired by 2 major Social Sciences approaches on group emotion (i.e., Top-down and Bottom-up), these architectures exploit cohesion and emotion interdependencies intending to improve the prediction of the dynamics (i.e. changes over time) of the Social and Task dimensions of cohesion. Emotion, here, is addressed in terms of its valence. Both architectures are evaluated against the performances of a similar model that only predicts the dynamics of both the Social and Task dimensions of cohesion, without integrating valence. Statistical analysis shows that only the deep model implementing the Bottom-up approach significantly improved the predictions of the Task cohesion’s dynamics. This result confirms the theoretical and practical benefits of multitasking as it takes full advantage of the inherent relationships between group emotion and cohesion to improve Task cohesion’s predictions.},
 keywords={Group Cohesion, Group Dynamics, Group Emotion, Multimodal Interaction, Multitask Learning},
 organization={IEEE},
 ISSN={2156-8111},
 url = {https://doi.org/10.1109/ACII52823.2021.9597429},
 url_Paper = {https://lucienmaman.github.io/files/available.pdf}
}

{"_id":"c9veGRRQzjqfS6mqt","bibbaseid":"maman-chetouani-likformansulem-varni-usingvalenceemotiontopredictgroupcohesionsdynamicstopdownandbottomupapproaches-2021","author_short":["Maman, L.","Chetouani, M.","Likforman-Sulem, L.","Varni, G."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Maman"],"firstnames":["Lucien"],"suffixes":[]},{"propositions":[],"lastnames":["Chetouani"],"firstnames":["Mohamed"],"suffixes":[]},{"propositions":[],"lastnames":["Likforman-Sulem"],"firstnames":["Laurence"],"suffixes":[]},{"propositions":[],"lastnames":["Varni"],"firstnames":["Giovanna"],"suffixes":[]}],"booktitle":"2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII)","title":"Using Valence Emotion to Predict Group Cohesion’s Dynamics: Top-down and Bottom-up Approaches","year":"2021","pages":"1-8","abstract":"Cohesion is an affective group phenomenon. It has received a lot of attention from scholars both in Social Sciences and in Affective Computing that showed that cohesion and emotion influence each other, highlighting the need to jointly analyze them. This study presents 2 deep neural network architectures grounded on multitask learning to jointly predict cohesion and emotion. Inspired by 2 major Social Sciences approaches on group emotion (i.e., Top-down and Bottom-up), these architectures exploit cohesion and emotion interdependencies intending to improve the prediction of the dynamics (i.e. changes over time) of the Social and Task dimensions of cohesion. Emotion, here, is addressed in terms of its valence. Both architectures are evaluated against the performances of a similar model that only predicts the dynamics of both the Social and Task dimensions of cohesion, without integrating valence. Statistical analysis shows that only the deep model implementing the Bottom-up approach significantly improved the predictions of the Task cohesion’s dynamics. This result confirms the theoretical and practical benefits of multitasking as it takes full advantage of the inherent relationships between group emotion and cohesion to improve Task cohesion’s predictions.","keywords":"Group Cohesion, Group Dynamics, Group Emotion, Multimodal Interaction, Multitask Learning","organization":"IEEE","issn":"2156-8111","url":"https://doi.org/10.1109/ACII52823.2021.9597429","url_paper":"https://lucienmaman.github.io/files/available.pdf","bibtex":"@inproceedings{maman-2021-acii, \n author={Maman, Lucien and Chetouani, Mohamed and Likforman-Sulem, Laurence and Varni, Giovanna}, \n booktitle={2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII)}, \n title={Using Valence Emotion to Predict Group Cohesion’s Dynamics: Top-down and Bottom-up Approaches}, \n year={2021}, \n pages={1-8},\n abstract={Cohesion is an affective group phenomenon. It has received a lot of attention from scholars both in Social Sciences and in Affective Computing that showed that cohesion and emotion influence each other, highlighting the need to jointly analyze them. This study presents 2 deep neural network architectures grounded on multitask learning to jointly predict cohesion and emotion. Inspired by 2 major Social Sciences approaches on group emotion (i.e., Top-down and Bottom-up), these architectures exploit cohesion and emotion interdependencies intending to improve the prediction of the dynamics (i.e. changes over time) of the Social and Task dimensions of cohesion. Emotion, here, is addressed in terms of its valence. Both architectures are evaluated against the performances of a similar model that only predicts the dynamics of both the Social and Task dimensions of cohesion, without integrating valence. Statistical analysis shows that only the deep model implementing the Bottom-up approach significantly improved the predictions of the Task cohesion’s dynamics. This result confirms the theoretical and practical benefits of multitasking as it takes full advantage of the inherent relationships between group emotion and cohesion to improve Task cohesion’s predictions.},\n keywords={Group Cohesion, Group Dynamics, Group Emotion, Multimodal Interaction, Multitask Learning},\n organization={IEEE},\n ISSN={2156-8111},\n url = {https://doi.org/10.1109/ACII52823.2021.9597429},\n url_Paper = {https://lucienmaman.github.io/files/available.pdf}\n}\n\n","author_short":["Maman, L.","Chetouani, M.","Likforman-Sulem, L.","Varni, G."],"key":"maman-2021-acii","id":"maman-2021-acii","bibbaseid":"maman-chetouani-likformansulem-varni-usingvalenceemotiontopredictgroupcohesionsdynamicstopdownandbottomupapproaches-2021","role":"author","urls":{"Paper":"https://doi.org/10.1109/ACII52823.2021.9597429"," paper":"https://lucienmaman.github.io/files/available.pdf"},"keyword":["Group Cohesion","Group Dynamics","Group Emotion","Multimodal Interaction","Multitask Learning"],"metadata":{"authorlinks":{}},"downloads":18,"html":""},"bibtype":"inproceedings","biburl":"https://lucienmaman.github.io/publications/my_publications_bibbase.bib","dataSources":["qHuuHpohSBrTjkfwF"],"keywords":["group cohesion","group dynamics","group emotion","multimodal interaction","multitask learning"],"search_terms":["using","valence","emotion","predict","group","cohesion","dynamics","top","down","bottom","approaches","maman","chetouani","likforman-sulem","varni"],"title":"Using Valence Emotion to Predict Group Cohesion’s Dynamics: Top-down and Bottom-up Approaches","year":2021,"downloads":18}