|
A social-functional view on the recognition and analysis of emotional expressions| title | A social-functional view on the recognition and analysis of emotional expressions |
|---|
| start_date | 2025/09/22 |
|---|
| schedule | 14h |
|---|
| online | no |
|---|
| location_info | salle 304 / Online |
|---|
| summary | Despite consensus among emotion researchers that the social meaning of emotional expressions is contextual, other-directed, co-constructed, and culturally dependent, computational methods largely rest on the assumption that expressions denote some internal state (e.g., emotion or pain) that can be inferred from an expression’s morphology or timing alone. For example, many affective computing papers adopt a classic detection perspective, in which observers annotate the presumed internal states revealed by an expression, and algorithms are then trained to predict this mapping without access to the original context in which the expression was produced. This assumption is also implicit in government regulations, such as the EU’s
AI Act, which bans emotion recognition across many practical applications. Although social psychology theorists advocate for a broader perspective on expressions, they often fail to provide detailed definitions of “context” or “co-construction” at a level that can be
operationalized by computational methods. In this talk, I will highlight the use of automatic expression analysis in social domains, emphasizing the interpersonal processes that shape their production and interpretation. I hope this talk encourages future work that formalizes the computational implications of this social perspective, including clarifying the communicative function of expressions, understanding how they are shaped and co-constructed through context and culture, and exploring how socially interactive agents might adapt and engage in meaning creation. |
|---|
| responsibles | Bawden |
|---|
Workflow history| from state (1) | to state | comment | date |
| submitted | published | | 2025/09/10 08:32 UTC |
| |
|