Fusing Audio, Textual and Visual Features for Sentiment Analysis of News Videos

TL;DR

This paper introduces a multi-modal sentiment analysis method for news videos by fusing audio, visual, and textual features, achieving high accuracy and aiding media analysis.

Contribution

It presents a novel fusion approach combining emotion recognition, speech modulation, and caption sentiment analysis for news video sentiment classification.

Findings

Achieved up to 84% accuracy in sentiment classification.

Effective fusion of audio, visual, and textual features.

Demonstrated potential for journalistic and media analysis applications.

Abstract

This paper presents a novel approach to perform sentiment analysis of news videos, based on the fusion of audio, textual and visual clues extracted from their contents. The proposed approach aims at contributing to the semiodiscoursive study regarding the construction of the ethos (identity) of this media universe, which has become a central part of the modern-day lives of millions of people. To achieve this goal, we apply state-of-the-art computational methods for (1) automatic emotion recognition from facial expressions, (2) extraction of modulations in the participants' speeches and (3) sentiment analysis from the closed caption associated to the videos of interest. More specifically, we compute features, such as, visual intensities of recognized emotions, field sizes of participants, voicing probability, sound loudness, speech fundamental frequencies and the sentiment scores (polarities) from text sentences in the closed caption. Experimental results with a dataset containing 520 annotated news videos from three Brazilian and one American popular TV newscasts show that our approach achieves an accuracy of up to 84% in the sentiments (tension levels) classification task, thus demonstrating its high potential to be used by media analysts in several applications, especially, in the journalistic domain.