Abstract
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.
| Original language | English |
|---|---|
| Article number | 6487473 |
| Pages (from-to) | 46-53 |
| Number of pages | 8 |
| Journal | IEEE Intelligent Systems |
| Volume | 28 |
| Issue number | 3 |
| DOIs | |
| State | Published - 2013 |
Keywords
- affective computing
- audio-visual pattern recognition
- intelligent systems
- linguistic analysis
- sentiment analysis