The Community for Technology Leaders
Green Image
Issue No. 03 - May-June (2013 vol. 28)
ISSN: 1541-1672
pp: 46-53
Martin Wollmer , Technische Universität München
Felix Weninger , Technische Universität München
Tobias Knaup , Technische Universität München
Bjorn Schuller , Technische Universität München
Congkai Sun , Shanghai Jiaotong University
Kenji Sagae , University of Southern California
Louis-Philippe Morency , University of Southern California
This work focuses on automatically analyzing a speaker's sentiment in online videos containing movie reviews. In addition to textual information, this approach considers adding audio features as typically used in speech-based emotion recognition as well as video features encoding valuable valence information conveyed by the speaker. Experimental results indicate that training on written movie reviews is a promising alternative to exclusively using (spoken) in-domain data for building a system that analyzes spoken movie review videos, and that language-independent audio-visual analysis can compete with linguistic analysis.
Videos, Motion pictures, Pragmatics, Context awareness, Feature extraction, YouTube, Visualization

M. Wollmer et al., "YouTube Movie Reviews: Sentiment Analysis in an Audio-Visual Context," in IEEE Intelligent Systems, vol. 28, no. 3, pp. 46-53, 2013.
380 ms
(Ver 3.3 (11022016))