한국융합학회논문지 (Journal of the Korea Convergence Society)

  • 제9권7호
  • /
  • Pages.25-31
  • /
  • 2018
  • /
  • 2233-4890(pISSN)
  • /
  • 2713-6353(eISSN)
한국융합학회 (Korea Convergence Society)
권호 표지
DOI QR코드

DOI QR Code

온라인 뉴스에 대한 한국 대중의 감정 예측

Inference of Korean Public Sentiment from Online News

  • 투고 : 2018.04.25
  • 심사 : 2018.07.20
  • 발행 : 2018.07.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

온라인 뉴스는 기존의 신문을 대체하였고, 우리가 정보에 접근하고 공유하는 방법에 큰 변화를 가져왔다. 뉴스 웹사이트들은 사용자가 댓글을 남길 수 있는 기능을 오랜 시간동안 제공하였고, 그 중 몇몇 뉴스 웹사이트에서는 뉴스 기사들에 대한 사용자의 반응들을 크라우드소싱(crowdsource)하기 시작했다. 감정분석 분야에서는 텍스트에 반영된 감정과 반응들을 컴퓨팅적으로 모델링하기 위한 시도를 하고 있다. 본 연구에서는 뉴스 기사에 대한 반응들이 뉴스 본문과 수학적인 상관관계를 갖는지 밝히기 위해, 사용자로부터 생성된 다섯 가지의 감정 라벨(label)을 사용하여 10가지 카테고리(category)에 해당하는 100,000개 이상의 뉴스 기사들을 분석한다. 본 연구에서는 전처리과정이 최소한으로 필요하고 기계학습이 적용하지 않아도 되는 간단한 감정 분석 알고리즘(algorithm)을 제안한다. 우리는 이 모델이 한국어와 같은 형태론적으로 복잡한 언어에도 효과적이라는 것을 증명한다.

Online news has replaced the traditional newspaper and has brought about a profound transformation in the way we access and share information. News websites have had the ability for users to post comments for quite some time, and some have also begun to crowdsource reactions to news articles. The field of sentiment analysis seeks to computationally model the emotions and reactions experienced when presented with text. In this work, we analyze more than 100,000 news articles over ten categories with five user-generated emotional annotations to determine whether or not these reactions have a mathematical correlation to the news body text and propose a simple sentiment analysis algorithm that requires minimal preprocessing and no machine learning. We show that it is effective even for a morphologically complex language like Korean.

키워드

참고문헌

  1. K. H. Lin, C. Yang & H. H. Chen. (2007). What Emotions do News Articles Trigger in their Readers? Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 38(6), 733-734.
  2. J. S. Song & S. W. Lee (2011). Automatic Construction of Positive/Negative Feature-Predicate Dictionary for Polarity Classification of Product Reviews. Journal of KIISE: Software and Applications, 38(3), 157-168.
  3. J. S. Myung, D. J Lee & S. G. Lee (2007). A Korean Product Review Analysis System Using a Semi-Automatically Constructed Semantic Dictionary. Proceedings of the 19th Annual Conference on Human and Cognitive Language Technology, 68-75.
  4. C. H. Jeong, J. H. Kim, Y. J. Jeon & H. J. Jeong (2017). Korean Sentiment Dictionary Based on the Reliability of Review Data. Journal of Korean Institute of Information Scientists and Engineers, 1965-1967.
  5. J. H. Seo, J. H Cho & J. T. Choi (2015). Design for Opinion Dictionary of Emotion Applying Rules for Antonym of the Korean Grammar. Journal of Advanced Information Technology and Convergence, 13(2), 109-117.
  6. X. Fang & J. Zhan. (2015). Sentiment Analysis Using Product Review Data. Journal of Big Data, 2(1), 5. https://doi.org/10.1186/s40537-015-0015-2
  7. B. Pang, L. Lee & S. Vaithyanahtan (2002). Thumbs Up?: Sentiment Classification using Machine Learning Techniques. Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, volume 10, 79-86.
  8. A. Pak & P. Paroubek (2010). Twitter as a Corpus for Sentiment Analysis and Opinion Mining. LREc, 10.
  9. L. Qu, G. Ifrim & G. Weikum (2010). The Bag-of-Opinions Method for Review Rating Prediction from Sparse Text Patterns. Proceedings of the 23rd International Conference on Computational Linguistics. Association for Computational Linguistics, 913-921.
  10. S. Baccianella, A. Esuli & F. Sebastiani. (2009). Multi-Facet Rating of Product Reviews. European Conference on Information Retrieval, 461-472.
  11. J. S. Kim (2016). Emotion Prediction of Paragraph using Big Data Analysis. Korea Convergence Society, 14(11), 267-273.
  12. P. Katz, M. Singleton & R. Wicentowski. (2007). SWAT-MP: The SemEval-2007 Systems for Task 5 and Task 14. Proceedings of the 4th International Workshop on Semantic Evaluations. Association for Computational Linguistics, 308-313.
  13. C. Strapparava & R. Mihalcea (2007). SemEval-2007 Task 14: Affective Text. Proceedings of the 4th International Workshop on Semantic Evaluations. Association for Computational Linguistics, 70-74.
  14. Y. Rao, J. Lei, L. Wenyin, Q. Li & M. Chen (2014). Building Emotional Dictionary for Sentiment Analysis of Online News. World Wide Web, 17(4), 723-742. https://doi.org/10.1007/s11280-013-0221-9
  15. J. O. Kim, S. S Lee & H. S. Yong. (2011). Automatic Classification Scheme of Opinions Written in Korean. Journal of Korean Institute of Information Scientists and Engineers, 38(6), 423-428.
  16. Y. A. Heo, D. Y. Lee & G. G. Kim (2017). A System for Automatic Classification of Traditional Texts. Korea Convergence Society, 8(12), 39-47.
  17. Bao, S., Xu, S., Zhang, L., Yan, R., Su, Z., Han, D., Yu, Y (2011). Mining Social Emotions from Affective Text. IEEE Transactions on Knowledge and Data Engineering, 24, 1658-1670.
  18. S. Bao, S. Xu, L. Zhang, R. Yan, Z. Su, D. Han & Y. Yu, (2009). Joint Emotion-Topic Modeling for Social Affective Text Mining. Proceedings of the 9th IEEE International Conference on Data Mining, 699-704.