Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Emotions in Broadcast News Using Convolutional Neural Networks

CNN을 활용한 방송 뉴스의 감정 분석

  • Nam, Youngja (Humanities Research Institute, Chung-Ang University)
  • Received : 2020.07.02
  • Accepted : 2020.07.10
  • Published : 2020.08.31
Download PDF
⟨ Previous Next ⟩

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.

한국의 영상기반 뉴스 미디어는 크게 지상파 방송, 종합편성 방송, 그리고 유튜브 방송과 같은 온라인 미디어로 나뉘어진다. 최근 이들 미디어의 방송 뉴스는 특정 시청자를 목표로 삼아 공정성과 중립성을 기대할 수 없는 주관적, 감정적인 성향의 내용을 송출하는 경향이 있다는 지적을 받고 있다. 이러한 양상은 시청자의 이슈 지각에 부정적인 영향을 미칠 수 있다. 이에 본 연구는 그 결과는 영상기반 미디어 뉴스 유형별로 감정 유형을 드러내는 성향의 차이가 존재하는지, 그리고 만약 차이가 존재한다면, 그 양상은 어떠한지를 살펴보았다. 감정 유형은 '딥러닝' 기법인 Convolutional Neural Network를 사용하여 중립, 행복, 슬픔 그리고 분노와 관련하여 분석하였다. 분석 결과, 전반적으로 뉴스 보도가 감정을 드러내는 성향이 있음을 보여주었다. 본 연구는 방송 뉴스에서 표출되는 감정을 다룬 첫 양적 연구이자 방송 뉴스 감정 분석에서 딥러닝을 사용한 첫 사례이다.

Keywords

References

  1. W. S. Lee, and J. Park, "Language and Expression in Broadcasting News: Focus on Objectivity and Fairness of News Language," Broadcasting & Communication, vol. 14, no. 1, pp. 5-46, Mar. 2013.
  2. E. Cho, and S. K. Yu, "A Study on the Diversity of News Coverage among TV Channels: Focusing on the Diversity of Railway Strike News Coverage," Korean Journal of Journalism & Communication Studies, vol. 58, no. 3, pp. 433-461, Jun. 2014.
  3. M. H. Kang, "A comparative study on the news characteristics between over-the-air broadcasters and general programming channels," Journal of Communication Science, vol. 16, no. 1, pp. 5-36, Mar. 2016. https://doi.org/10.14696/jcs.2016.03.16.1.5
  4. S. Yang, "Reality and Challenges of Traditional Journalism in the Era of YouTube Journalism," Journal of Social Science, vol. 31, no. 1, pp. 245-262, Jan. 2020. https://doi.org/10.16881/jss.2020.01.31.1.245
  5. J. H. Hong, "Network Analysis and Frame Analysis on the Sensationalism of News Coverage according to the Influence of News Production Environment: based on the #metoo movement of celebrity," Journal of the Korea Contents Association, vol. 18, no. 7, pp. 103-119, Sep. 2018. https://doi.org/10.5392/JKCA.2018.18.07.103
  6. H. Lee, and H. Yu, "An Exploratory Study on Negative Characteristics of Multi Channel Network Content, and Introduction of Relevant Regulations," Journal of Speech, Media & Communication Research, vol. 16, no. 1, pp. 119-152, 2017. https://doi.org/10.22902/JSMCR.2017.16.1.004
  7. S. J. Kim, and Y. Chung, "Influences of sensational TV news on viewers' emotion, memory, news evaluation, and perception of social conflict," Media & Performing Arts, vol. 9, no. 3, pp. 118-130, Dec. 2014.
  8. Y. J. Lee, "A study on the effect of TV news anchor's words on the reaction of viewers," Mater's thesis, The Graduate School of Mass Communication, Yonsei University, Dec. 2004.
  9. P. Sermanet, and Y. L. Cun, "Traffic sign recognition with multi-scale convolutional networks," In The 2011 International Joint Conference on Neural Networks, pp. 2809-2813, IEEE, Jul. 2011.
  10. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, "Going deeper with convolutions," In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015.
  11. S. Abdoli, P. Cardinal, and A. L. Koerich, "End-to-end environmental sound classification using a 1D convolutional neural network," Expert Systems with Applications, vol. 136, pp. 252-263, Dec. 2019. https://doi.org/10.1016/j.eswa.2019.06.040
  12. W. Q. Zheng, J. S. Yu, and Y. X. Zou, "An experimental study of speech emotion recognition based on deep convolutional neural networks," In The 2015 International conference on affective computing and intelligent interaction (ACII), pp. 827-831, 2015.
  13. S. Ahn, and W. Yoo, "The Influence of TV News Brand Equity Evaluation on Channel Loyalty and the Mediating Effect of TV News Loyalty: KBS and JTBC TV News," The Korean Journal of Advertising, vol. 29, no. 2, pp. 55-78, 2018. https://doi.org/10.14377/KJA.2018.2.28.55
  14. S. Kim, H. Shim, and Y. H. Park, "Analyzing the causes of decrease in journalism credibility and examining the achievement of credibility in broadcasting reportage through media accountability in Korea," Korea Communications Commission, Technical Report KCC-2018-39, Dec. 2018.