DOI QR코드

DOI QR Code

게임 도메인 웹 코퍼스를 이용한 감성사전 구축 및 평가

Construction and Evaluation of a Sentiment Dictionary Using a Web Corpus Collected from Game Domain

  • 정우영 (홍익대학교 대학원 게임학과(공학)) ;
  • 배병철 (홍익대학교 대학원 게임학과(공학)) ;
  • 조성현 (홍익대학교 대학원 게임학과(공학)) ;
  • 강신진 (홍익대학교 대학원 게임학과(공학))
  • 투고 : 2018.03.20
  • 심사 : 2018.10.10
  • 발행 : 2018.10.20

초록

본 논문은 게임 도메인에서 웹 코퍼스를 이용하여 감성사전을 구축하는 방법과 구축한 감성사전의 평가 결과를 기술한다. 감성사전 구축을 위해 먼저 트위터 형태소 분석기를 이용해 국내 한 포털 사이트의 게임 관련 웹 문서를 기반으로 어휘를 수집하여 감성 사전 어휘 목록을 만들었고, 목록에 있는 단어들 중 동사와 형용사 품사의 단어들에 대해 감성 사전을 구축하였다. 구축된 감성 사전의 평가를 위해 영어 기반의 Senti-word Net(SWN)을 한글로 번역한 한국어 SWN을 이용하여 정밀도와 재현율 값을 계산하였다. 평가 결과 긍정과 부정 감성의 F-1 값에 대한 평균이 형용사의 경우 0.85, 동사에 대해 0.77을 각각 보여 주었다.

This paper describes an approach to building and evaluating a sentiment dictionary using a Web corpus in the game domain. To build a sentiment dictionary, we collected vocabulary based on game-related web documents from a domestic portal site, using the Twitter Korean Processor. From the collected vocabulary, we selected the words whose POS are tagged as either verbs or adjectives, and assigned sentiment score for each selected word. To evaluate the constructed sentiment dictionary, we calculated F1 score with precision and recall, using Korean-SWN that is based on English Senti-word Net(SWN). The evaluation results show that average F1 scores are 0.85 for adjectives and 0.77 for verbs, respectively.

키워드

참고문헌

  1. 성동형, 이병기, "Research Trends in Clinical Natural Language Processing", Communications of the Korean Institute of Information Scientists and Engineers, Vol.35, No.5, pp.20-26, 2017.5
  2. 조은경, "Extracting Lexical functional words and Aboutness in Sentiment Analysis", 한국어의미학회, Vol.47, No.0, pp.1-26, 2015.3 https://doi.org/10.19033/sks.2015.03.47.1
  3. Sukjae Choi, Ohbyung Kwon, "The Study of Developing Korean SentiWordNet for Big Data Analytics : Focusing on Anger Emotion", The Journal of Society for e-Business Studies, Vol.19, No.4, pp.1-19, 2014.12 https://doi.org/10.7838/JSEBS.2014.19.4.001
  4. 장문수, "Problems of Natural Language Processing for Spoken Language and an Approach of Systemic Functional Grammatical Solution", Korean Linguistics Vol.46, pp.123-143, 2010.2
  5. Bo Pang, Lillian Lee."Thumbs up?: sentiment classification using machine learning techniques", Proceedings of the Conference on Empirical Methods in Natural Language Processing, Vol. 10, pp.79-86, 2002.7
  6. Peter D. Turney, "Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews", Proceedings of the 40th annual meeting on association for computational linguistics, pp.417-424, 2002.7
  7. Stefano Baccianella, Andrea Esuli, Fabrizio Sebastiani, "SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining", LREC, Vol. 10, pp. 2200-2204, 2010.1
  8. Jungkook An, Hee-Woong Kim, "Building a Korean Sentiment Lexicon Using Collective Intelligence", Journal of Intelligence and Information Systems, pp. 49-67, 2015.6
  9. Claudiu-Cristian Musat, Alireza Ghasemi, Boi Faltings, "Sentiment analysis using a novel human computation game", Proceedings of the 3rd Workshop on the People's Web Meets NLP: Collaboratively Constructed Semantic Resources and their Applications to NLP, pp. 1-9, 2012.7
  10. Marco Furini, Manuela Montangero, "TSentiment: on gamifying Twitter sentiment analysis", Computers and Communication (ISCC), IEEE Symposium on, pp. 91-96, 2016.6
  11. Yoonsung Hong, Haewoon Kwak, Youngmin Baek, Sue Moon, "Tower of Babel: A crowdsourcing game building sentiment lexicons for resource-scarce languages", Korea Game Society, pp. 135-144, 2017.5
  12. Jun-Gi Kim, Shin-Jin Kang, Byung-Chull Bae "A Crowdsourcing-based Emotional Words Tagging Game for Building a Polarity Lexicon in Korean", Graduate School of Culture, Information, and Public Policy, Vol. 13, No. 2, pp.135-144, 2017.4
  13. Jungkook An, Hee-Woong Kim, "Building a Korean Sentiment Lexicon Using Collective Intelligence", Korea Intelligent Information Systems Society, Vol.21, No.2, pp.49-67, 2015.6 https://doi.org/10.13088/jiis.2015.21.2.49
  14. Donghyok Shin, Sairom Kim, Donghee Cho, Minh Dieu Nguyen, Soongang Park, Keonjoo Eo, Jeesun Nam, "Performance and Limitations of a Korean Sentiment Lexicon Built on the English SentiWordNet", Korean Language Information Science Society, Vol.28, pp.189-194, 2016.7
  15. 이상훈, 최정, 김종우, "Sentiment analysis on movie review through building modified sentiment dictionary by movie genre", J Intell Inform Syst, Vol.22, No.2, pp.97-113, 2016.6 https://doi.org/10.13088/JIIS.2016.22.2.097
  16. Jae-Young Chang, "A Sentiment Analysis Algorithm for Automatic Product Reviews Classification in On-Line Shopping Mall", The Journal of Society for e-Business Studies, Vol.14, No.4, pp.19-33, 2009.11
  17. Woo Chul Lee, Hyun Ah Lee, Kong Joo Lee, "Product Evaluation Summarization Through Linguistic Analysis of Product Reviews", Korea Information Processing Society, Vol.17B, Issue 1, pp.93-98, 2010
  18. Jae-Khun Chang, Seung-Taek Ryoo, Dong-In Jang, "Similar Image Extraction using Emotional Classification of Image Contents", Korea Game Society, Vol.25, No.2, pp.183-188, 2012.6
  19. Heekyung Yang, Hyuksung Yang, Kyugha Min, "Enhancing Emotion of Visual Contents Based on Emotion Model For Elevating Absorption Degree of Games", Korea Game Society, Vol.25, No.2, pp.171-176, 2012.6
  20. Minyoung Kim, Kyoung Shin Park, Dongkeun Kim, Yongjoo Cho, "Open Source Library based Emotional Game Engine and Emotion Sharing Game Contents", Korea Game Society, Vol.25, No.3, pp.15-24, 2012.9
  21. Suk Jin Kim, Yong Sung Kim, "Game Application Tendency Analysis Based on Bigdata and Emotional color Adjective", Korea Game Society, Vol.29, No.4, pp.177-185, 2016.12
  22. Vasileios Hatzivassiloglou, Kathleen R. McKeown., "Predicting the Semantic Orientation of Adjectives", In Proceedings of ACL-97, 35th Annual Meeting of the Association for Computational Linguistics, pp.174-181, 1997.7
  23. Hyun Won Jung, Ken Nah, "A Study on the Meaning of Sensibility and Vocabulary System for Sensibility Evaluation", Journal of the Ergonomics Society of Korea, Vol.26, No.3 pp.17-25, 2007.8 https://doi.org/10.5143/JESK.2007.26.3.017