Journals & Magazines >IEEE Intelligent Systems >Volume: 28 Issue: 3

Multimodal Sentiment Analysis of Spanish Online Videos

Download PDF
Download References
Request Permissions
Save to
Alerts

Abstract:

Using multimodal sentiment analysis, the presented method integrates linguistic, audio, and visual features to identify sentiment in online videos. In particular, experim...Show More

Metadata

Abstract:

Using multimodal sentiment analysis, the presented method integrates linguistic, audio, and visual features to identify sentiment in online videos. In particular, experiments focus on a new dataset consisting of Spanish videos collected from YouTube that are annotated for sentiment polarity.

Published in: IEEE Intelligent Systems ( Volume: 28, Issue: 3, May-June 2013)

Page(s): 38 - 45

Date of Publication: 24 January 2013

ISSN Information:

DOI: 10.1109/MIS.2013.9

Verónica Pérez Rosas

Instituto Tecnólogico de Ciudad Madero, University of North Texas, USA

Veronica Perez Rosfs is a doctoral student in the Department of Computer Science and Engineering at the University of North Texas. Her research interests include natural language processing, machine learning, and intelligent optimization. Perez Rosas has an MS in computer science from the Instituto Tecnologico de Ciudad Madero. Contact her at veronicaperezrosas@my.unt.edu.

Rada Mihalcea

Department of Electrical Engineering and Computer Science, University of Michigan, USA

Louis-Philippe Morency

Department of Computer Science, University of Southern California, USA

Contents

A Spanish Multimodal Opinion Dataset

We collected a new dataset consisting of 105 videos in Spanish from the social media website YouTube. An important characteristic of our dataset is its generalized nature; the dataset is created in such a way that it's not based on one particular topic. We found the videos using the following keywords: mi opinion (my opinion), mis products favoritos (my favorite products), me gusta (I like), no me gusta (I dislike), products para bebe (baby products), mis perfumes favoritos (my favorite perfumes), peliculas recomendadas (recommended movies), opinion politica (political opinion), video juegos (video games), and abuso animal (animal abuse). To select the videos, we used the following guidelines: people should be in front of the camera; their face should be visible; there shouldn't be any background music or animation. Figure 2 shows example snapshots from our dataset.

Verónica Pérez Rosas

Instituto Tecnólogico de Ciudad Madero, University of North Texas, USA

Rada Mihalcea

Department of Electrical Engineering and Computer Science, University of Michigan, USA

Rada Mihalcea is an associate professor in the Department of Electrical Engineering and Computer Science at the University of Michigan. Her research interests are in computational linguistics, with a focus on lexical semantics, graph-based algorithms for natural language processing, and multilingual natural language processing. Mihalcea has a PhD in computer science and engineering from Southern Methodist University and a PhD in linguistics from Oxford University. She is the recipient of a National Science Foundation Career award and a Presidential Early Career Award for Scientists and Engineers. Contact her at mihalcea@umich.edu.

Louis-Philippe Morency

Department of Computer Science, University of Southern California, USA

Louis-Philippe Morency is a research assistant professor in the Department of Computer Science at the University of Southern California (USC) and research scientist at the USC Institute for Creative Technologies, where he leads the Multimodal Communication and Machine Learning Laboratory. His research interests focus on the computational study of nonverbal social communication, a multidisciplinary research topic that overlays the fields of multimodal interaction, computer vision, machine learning, social psychology, and artificial intelligence. Morency has a PhD in computer science and artificial intelligence from MIT. In 2008, IEEE Intelligent Systems selected him as one of the “10 to watch” for the future of AI research. Contact him at morency@ict.usc.edu.

References is not available for this document.

Multimodal Sentiment Analysis of Spanish Online Videos

Abstract:

Metadata

Abstract:

ISSN Information:

A Spanish Multimodal Opinion Dataset

References

IEEE Account

Purchase Details

Profile Information

Need Help?

Multimodal Sentiment Analysis of Spanish Online Videos

Alerts

Abstract:

Metadata

Abstract:

ISSN Information:

A Spanish Multimodal Opinion Dataset

References