Study of attention mechanisms for computational models of cohesion
Siboyabasore, Cédric
Promotor(s) : Ittoo, Ashwin
Date of defense : 26-Jun-2023/27-Jun-2023 • Permalink : http://hdl.handle.net/2268.2/16806
Details
Title : | Study of attention mechanisms for computational models of cohesion |
Translated title : | [fr] Étude de mécanismes d'attentions pour des modèles computationnelles de la cohésion |
Author : | Siboyabasore, Cédric |
Date of defense : | 26-Jun-2023/27-Jun-2023 |
Advisor(s) : | Ittoo, Ashwin |
Committee's member(s) : | Geurts, Pierre
Debruyne, Christophe |
Language : | English |
Number of pages : | 70 |
Keywords : | [en] Natural Language Processing [en] Attention [en] Groups |
Discipline(s) : | Engineering, computing & technology > Computer science |
Research unit : | Télécom Paris |
Target public : | Researchers Student |
Institution(s) : | Université de Liège, Liège, Belgique |
Degree: | Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems" |
Faculty: | Master thesis of the Faculté des Sciences appliquées |
Abstract
[fr] Social Signal Processing is a new interdisciplinary domain of research whose end goal is to equip
machines with social intelligence, a facet of intelligence only known to mankind. As life happens
in groups, it is essential that machines understand how human groups function to be able to
collaborate with them in the future. One important aspect of group life is group cohesion. In
the social sciences literature, several definitions of cohesion exist. In our work, we use Severt and
Estrada’s integrative framework of cohesion. Recently, Maman et al. developed a computational
model of cohesion called fItG that automatically predict the dynamics of cohesion. However, this
model uses all interaction timestamps equally, without dynamically giving each of them a certain
importance.
In this work, we develop attention-based versions of fItG. We compare their performances with the
original fItG model through permutation tests of their F1-scores
File(s)
Document(s)
Description:
Size: 2.16 MB
Format: Adobe PDF
Cite this master thesis
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.