DocumentCode
3703288
Title
Adapting sentiment analysis to face-to-face human-agent interactions: From the detection to the evaluation issues
Author
Caroline Langlet;Chlo? Clavel
Author_Institution
Institut Mines-T?l?com, T?l?com ParisTech, CNRS LTCI, 46 Rue Barrault, 75013 Paris, France
fYear
2015
Firstpage
14
Lastpage
20
Abstract
This paper introduces a sentiment analysis method suitable to the human-agent and face-to-face interactions. We present the positioning of our system and its evaluation protocol according to the existing sentiment analysis literature and detail how the proposed system integrates the human-agent interaction issues. Finally, we provide an in-depth analysis of the results obtained by the evaluation, opening the discussion on the different difficulties and the remaining challenges of sentiment analysis in human-agent interactions.
Keywords
"Sentiment analysis","Protocols","Context","Pragmatics","Adaptation models","Machine learning algorithms","Semantics"
Publisher
ieee
Conference_Titel
Affective Computing and Intelligent Interaction (ACII), 2015 International Conference on
Electronic_ISBN
2156-8111
Type
conf
DOI
10.1109/ACII.2015.7344545
Filename
7344545
Link To Document