Insights Into the Importance of Linguistic Textual Features on the Persuasiveness of Public Speaking - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Insights Into the Importance of Linguistic Textual Features on the Persuasiveness of Public Speaking

Résumé

There is a growing need for public speaking skills in both professional and private life. With this background, our research project's long-term aims are to develop tools that can analyse public speeches and provide helpful feedback. The impact of audio and visual characteristics on the automatic analysis of speech quality has been widely explored in the existing literature. However, only a few studies have focused on textual features. In response to this shortcoming, this paper investigates the importance of textual content for the automatic analysis of public speaking. We created an open-source Python library of textual features and integrated them as inputs of simple machine-learning models for automatic public-speaking analysis, and persuasiveness prediction, in particular. The best result (accuracy of 61%) is obtained using a logistic regression. We then evaluated the impact of these features on persuasiveness prediction using both correlation analysis and Explainable AI methods. This evaluation was conducted on the French data set 3MT_French, including student performances in the "Ma Thèse en 180 Secondes" competition. CCS CONCEPTS • Computing methodologies → Classifcation and regression trees; Modeling and simulation.
Fichier principal
Vignette du fichier
ICMI_short_author_version.pdf (1.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04251755 , version 1 (20-10-2023)

Identifiants

Citer

Alisa Barkar, Mathieu Chollet, Beatrice Biancardi, Chloe Clavel. Insights Into the Importance of Linguistic Textual Features on the Persuasiveness of Public Speaking. 25th International Conference on Multimodal Interaction (iCMI 2023), Oct 2023, Paris, France. pp.51-55, ⟨10.1145/3610661.3617161⟩. ⟨hal-04251755⟩
85 Consultations
78 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More