Automatic Prediction of Impressions in Time and across Varying Context: Personality, Attractiveness and Likeability
- Submitting institution
-
King's College London
- Unit of assessment
- 12 - Engineering
- Output identifier
- 111339083
- Type
- D - Journal article
- DOI
-
10.1109/TAFFC.2015.2513401
- Title of journal
- IEEE transactions on affective computing
- Article number
- -
- First page
- 29
- Volume
- 8
- Issue
- 1
- ISSN
- 1949-3045
- Open access status
- Out of scope for open access requirements
- Month of publication
- December
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper introduces the MAPTRAITS system, the first-of-its kind, that can predict personality of a human conversing with a virtual agent in the course of interaction and deliver the predicted output for perceived personality in real-time. This is significant because ensuring user engagement and experience in human-AI interactions highly depends on the capability of agents adapting to user’s profiles. The MAPTRAITS system was subsequently applied to human-robot interaction (Celiktutan et. al, IEEE FG 2015), and was featured on Slovenian national TV. This work also led to the organisation of a challenge and workshop in conjunction with the ACM ICMI 2014.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -