디지털융복합연구 (Journal of Digital Convergence)

  • 제14권3호
  • /
  • Pages.165-170
  • /
  • 2016
  • /
  • 2713-6434(pISSN)
  • /
  • 2713-6442(eISSN)
한국디지털정책학회 (The Society of Digital Policy and Management)
권호 표지
DOI QR코드

DOI QR Code

SNS에서의 언어 간 감성 차이 연구: 6개 언어를 중심으로

Differences in Sentiment on SNS: Comparison among Six Languages

  • 투고 : 2016.02.01
  • 심사 : 2016.03.20
  • 발행 : 2016.03.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구의 목적은 SNS 활용에 있어 사용자 언어 간 감성의 평균차이가 있는지를 검증하는 것이다. 가장 많이 이용되는 SNS 중 하나인 트위터를 대상으로, 영어, 독일어, 러시아어, 스페인어, 터키어 및 네덜란드어 등 6개 언어로 작성된 약 2억 개 트윗을 스트리밍 API를 이용하여 수집하였으며, SentiStrength를 이용하여 주관적/객관적 비율, 감성강도, 긍정/부정 비율, 리트윗 횟수 및 경계불투과도 등에 대한 분석을 시행하고, 트위터를 통한 감성표현의 경향성과 변동을 파악하였다. 분석결과, 언어권에 따라 주관적/객관적 트윗 비율과 긍정/부정 트윗 비율이 각각 통계적으로 유의한 차이가 있는 것으로 나타났다(p<0.001). 또한, 언어의 종류는 감성강도와 경계 불투과도 그리고 리트윗 횟수에 통계적으로 유의한(p<0.001) 영향을 미치는 것으로 파악되었다. 이러한 결과는 SNS를 활용한 감성분석에 있어 언어, 문화 별 경향성 및 수준차이를 반드시 고려하여야 한다는 것을 보여준다.

The purpose of this study was to explore the differences in sentiment on social networking sites among six languages (English, German, Russian, Spanish, Turkish and Dutch). A total of 204 million tweets were collected using Streaming API. Subjective/objective ratio, sentiment strength, positive/negative ratio, number of retweets and boundary impermeability were analyzed with SentiStrength to estimate the trends of emotional expression via Twitter. The results showed that subjective/objective ratio and the positive/negative ratio of tweets were significantly different by languages (p<0.001). And, there were significant effects of language on sentiment strength, boundary impermeability and the number of retweets (p<0.001). The results also indicate that the cross-cultural, language differences should be taken into account in sentiment analysis on SNS.

키워드

참고문헌

  1. K. Choi, J. A. Yoo, "A reviews on the social network analysis using R", Journal of the Korea Convergence Society, Vol. 6, No. 1, pp. 77-83, 2015. https://doi.org/10.15207/JKCS.2015.6.1.077
  2. J. Y. Go, K. H. Lee, "SNS disclosure of personal information in M2M environment threats and countermeasures", Journal of the Korea Convergence Society, Vol. 5, No. 1, pp. 29-34, 2014. https://doi.org/10.15207/JKCS.2014.5.1.029
  3. B. Pang, and L. Lee, "Opinion mining and sentiment analysis", Foundations and Trends in Information Retrieval, Vol. 1. No. 2, pp. 1-135, 2008.
  4. P. S. Jang, "Study on principal sentiment analysis of social data", Journal of The Korea Society of Computer and Information, Vol. 19, No. 12, pp.49-56, 2014.
  5. D. M. Boyd and N. B. Ellison, N. B. "Social network sites: Definition, history, and scholarship", Journal of Computer-Mediated Communication, Vol. 13, No. 1. pp. 210-230, 2007 https://doi.org/10.1111/j.1083-6101.2007.00393.x
  6. J. J. Yoo, D. Kim and J. Moon, "Exploring cross-cultural differences in self-presentation and self-disclosure in social Networking sites: A comparison of korean and american SNS users", Journal of Advertising and Promotion Research, Vol. 1, No. 2, pp. 77-118, 2012.
  7. S. Luo, "Cross-cultural differences between American and Chinese college students on self-disclosure on social media. Graduate Theses and Dissertations", p.1-70, Iowa State University. 2014.
  8. K. Omori and M. Allen, "Cultural differences between american and japanese self-presentation on SNSs", International Journal of Interactive Communication Systems and Technologies (IJICST), Vol. 4, Issue 1. DOI: 10.4018/ijicst.2014010104, 2014.
  9. S. A. Golder and M. W. Macy, "Diurnal and seasonal mood vary with work, sleep and daylength across diverse cultures." Science, 333, pp. 1878-1881, 2011. https://doi.org/10.1126/science.1202775
  10. J. Y. Lee, P. S. Jang, "Effects of message polarity and type on word of mouth through SNS (Social Network Service)", The Journal of Digital Policy & Management, Vol. 11, No. 6, pp. 129-135, 2013.
  11. S. C. Walton and R. E. Rice, "Mediated disclosure on Twitter: The roles of gender and identity in boundary impermeability, valence, disclosure, and stage", Computers in Human Behavior, Vol. 29, pp. 1465-1474, 2013. https://doi.org/10.1016/j.chb.2013.01.033
  12. "The Streaming APIs", (C) 2016 Twitter, Inc., https://dev.twitter.com/streaming/overview (Jan 5, 2016)
  13. "MongoDB 3.2", MongoDB, Inc., https://www.mongodb.org/ (Jan 5, 2016)
  14. M. Thelwall, K. Buckley. & G. Paltoglou, "Sentiment strength detection for the social Web", Journal of the American Society for Information Science and Technology, Vol. 63, No. 1, pp. 163-173, 2012. https://doi.org/10.1002/asi.21662
  15. "SentiStrength", http://sentistrength.wlv.ac.uk/, (Jan 25, 2016)