Serial Number: http://www.riss.kr/link?id=A107283665

Title: Analysis of Emotions in Broadcast News Using Convolutional Neural Networks

Author: Nam Youngja

Journal: Journal of the Korea Institute Of Information and Communication Engineering

Vol: 24(8)

Pages: 1064-1070

Date: 2020.

Register Information: KCI

etc.: -
-----------------------------------------------------------------------

<Abstract>

In Korea, video-based news broadcasters are primarily classified into terrestrial broadcasters, general programming cable broadcasters and YouTube broadcasters. Recently, news broadcasters get subjective while targeting the desired specific audience. This violates normative expectations of impartiality and neutrality on journalism from its audience. This phenomenon may have a negative impact on audience perceptions of issues. This study examined whether broadcast news reporting conveys emotions and if so, how news broadcasters differ according to emotion type. Emotion types were classified into neutrality, happiness, sadness and anger using a convolutional neural network which is a class of deep neural networks. Results showed that news anchors or reporters tend to express their emotions during TV broadcasts regardless of broadcast systems. This study provides the first quantative investigation of emotions in broadcasting news. In addition, this study is the first deep learning-based approach to emotion analysis of broadcasting news.