Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos

Amir Zadeh, Rowan Zellers, Eli Pincus, Louis-Philippe Morency

TL;DR

This paper introduces to the scientific community the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos called Multimodal Opinion-level Sentiment Intensity dataset (MOSI), which is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, andper-milliseconds annotated audio features.

Abstract

People are sharing their opinions, stories and reviews through online video sharing websites every day. Studying sentiment and subjectivity in these opinion videos is experiencing a growing attention from academia and industry. While sentiment analysis has been successful for text, it is an understudied research question for videos and multimedia content. The biggest setbacks for studies in this direction are lack of a proper dataset, methodology, baselines and statistical analysis of how information from different modality sources relate to each other. This paper introduces to the scientific community the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos called Multimodal Opinion-level Sentiment Intensity dataset (MOSI). The dataset is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, and per-milliseconds annotated audio features. Furthermore, we present baselines for future studies in this direction as well as a new multimodal fusion approach that jointly models spoken words and visual gestures.

MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos

TL;DR

This paper introduces to the scientific community the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos called Multimodal Opinion-level Sentiment Intensity dataset (MOSI), which is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, andper-milliseconds annotated audio features.

Abstract

People are sharing their opinions, stories and reviews through online video sharing websites every day. Studying sentiment and subjectivity in these opinion videos is experiencing a growing attention from academia and industry. While sentiment analysis has been successful for text, it is an understudied research question for videos and multimedia content. The biggest setbacks for studies in this direction are lack of a proper dataset, methodology, baselines and statistical analysis of how information from different modality sources relate to each other. This paper introduces to the scientific community the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos called Multimodal Opinion-level Sentiment Intensity dataset (MOSI). The dataset is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, and per-milliseconds annotated audio features. Furthermore, we present baselines for future studies in this direction as well as a new multimodal fusion approach that jointly models spoken words and visual gestures.

Paper Structure

This paper contains 13 sections, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. MOSI: Multimodal Opinion-level Sentiment Intensity Corpus
  4. Acquisition Methodology
  5. Opinion-level Subjectivity Segmentation
  6. Sentiment Intensity Annotation
  7. Visual Gesture Annotation
  8. Multimodal analysis of words and visual gestures
  9. Sentiment and Subjectivity Analysis Baselines
  10. Sentiment Analysis Baselines
  11. Subjectivity Analysis Baselines
  12. Discussion
  13. Conclusion

Figures (3)

  • Figure 1: Example snapshots of videos from our new MOSI dataset.
  • Figure 2: Histogram in the left shows the distribution of sentiment over the entire dataset. The right graph shows the percentage of each sentiment degree per segment size (number of words in opinion segment).
  • Figure 3: Sentiment intensity histograms for different spoken words and visual gestures. In each histogram y-axis is the frequency of co-occurrence and x -axis is sentiment intensity as in Figure 2.