Affect detection from semantic and metaphorical interpretation of virtual drama

Zhang, Li, Barnden, John and Jiang, Ming (2013) Affect detection from semantic and metaphorical interpretation of virtual drama. In: AAMAS '13 - 2013 International Conference on Autonomous Agents and Multi-Agent Systems, 6th - 10th May 2013, Saint Paul, MN, USA.

[img]
Preview
Text (Full text)
Zhang et al - Affect detection from semantic and metaphorical interpretation of virtual drama AAM.pdf - Accepted Version

Download (578kB) | Preview
Official URL: https://dl.acm.org/citation.cfm?id=2485178

Abstract

We have developed an intelligent agent to engage with users in virtual drama improvisation previously. The agent was able to perform sentence-level affect detection especially from inputs with strong emotional indicators. In this research, we employ latent semantic analysis to interpret emotional expressions with vague affect indicators and ambiguous audiences. Latent semantic analysis is thus used to perform topic theme detection and target audience identification for such inputs. Then we also discuss how affect is detected for such inputs without strong emotional indicators with the consideration of emotions expressed by the intended audiences and relationships between speakers and audiences. This work also proves to be effective in recognizing metaphorical phenomena. Moreover, uncertainty-based active learning is also employed to deal with more open-ended and imbalanced affect detection tasks. Overall, this work enables the AI agent to deal with challenging issues in affect detection tasks.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Affect detection, latent semantic analysis, and improvisation
Subjects: G700 Artificial Intelligence
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 11 Dec 2018 11:19
Last Modified: 01 Aug 2021 09:35
URI: http://nrl.northumbria.ac.uk/id/eprint/37172

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics