DOI QR코드

DOI QR Code

Towards Next Generation Multimedia Information Retrieval by Analyzing User-centered Image Access and Use

이용자 중심의 이미지 접근과 이용 분석을 통한 차세대 멀티미디어 검색 패러다임 요소에 관한 연구

  • 정은경 (이화여자대학교 사회과학대학 문헌정보학과)
  • Received : 2017.10.16
  • Accepted : 2017.11.13
  • Published : 2017.11.30

Abstract

As information users seek multimedia with a wide variety of information needs, information environments for multimedia have been developed drastically. More specifically, as seeking multimedia with emotional access points has been popular, the needs for indexing in terms of abstract concepts including emotions have grown. This study aims to analyze the index terms extracted from Getty Image Bank. Five basic emotion terms, which are sadness, love, horror, happiness, anger, were used when collected the indexing terms. A total 22,675 index terms were used for this study. The data are three sets; entire emotion, positive emotion, and negative emotion. For these three data sets, co-word occurrence matrices were created and visualized in weighted network with PNNC clusters. The entire emotion network demonstrates three clusters and 20 sub-clusters. On the other hand, positive emotion network and negative emotion network show 10 clusters, respectively. The results point out three elements for next generation of multimedia retrieval: (1) the analysis on index terms for emotions shown in people on image, (2) the relationship between connotative term and denotative term and possibility for inferring connotative terms from denotative terms using the relationship, and (3) the significance of thesaurus on connotative term in order to expand related terms or synonyms for better access points.

멀티미디어 정보환경의 발전과 다양한 요구를 지닌 정보이용자는 멀티미디어의 접근과 이용에 있어서 기존 정보검색 패러다임에서 중요시하지 않았던 요소를 사용하는 추세이다. 특히 이미지를 포함한 멀티미디어의 감정 접근과 이용은 다양한 정보환경에서 이루어지고 있다. 따라서 효율적으로 추상적 개념인 감정을 이용자에게 접근점으로 제공할 필요성이 증가한다. 본 연구는 감정으로 접근이 가능한 게티 이미지 뱅크의 이미지를 5가지 기본 감정으로 검색하여 부여된 색인어 총 22,675건을 추출하였다. 추출된 색인어는 전체감정, 긍정감정, 부정감정의 세 가지 데이터셋으로 구분하여 분석되었다. 분석을 위해서는 동시출현단어행렬로 작성되어 가중 네트워크와 군집화기법으로 시각화되었다. 분석결과를 살펴보면, 전체감정은 대분류로써 긍정감정, 부정감정, 가족의 3개 군집과 하위 20개의 군집으로 나타났다. 긍정감정은 10개의 군집이며, 부정감정은 10개의 군집으로 구성되었다. 이와 같은 가중 네트워크와 군집구성 분석을 통해, 세 가지 중요한 차세대 멀티미디어 검색을 위한 요소로 논의하였다. 첫째는 이미지 감정 표현을 위한 인물 색인어 특성이다. 둘째는 명시적 단어와 감정을 표현하는 함축적 단어와의 네트워크 구성을 통해서 상대적으로 색인이 용이한 명시적 단어만으로도 함축적 단어 추론 가능성이다. 셋째는 감정으로 표현하는 함축적 단어의 유사어/동의어로의 확장은 이용자 중심의 접근을 제공하는 측면에서 중요하다는 점이다.

Keywords

References

  1. 이재윤. 2006. 지적 구조 분석을 위한 새로운 클러스터링 기법에 관한 연구. 정보관리학회지, 23(4): 215-231. (Lee, Jae-Yun. 2006. "A Novel Clustering Method for Examining and Analyzing the Intellectual Structure of a Scholarly Field." Journal of the Korean Society for Information Management, 23(4): 215-231.) https://doi.org/10.3743/KOSIM.2006.23.4.215
  2. 이재윤. COOC ver 0.4 프로그램 [cited 2017. 10. 7.] (Lee, Jae-Yun. COOC ver 0.4 Software. [cited 2017. 10. 7.])
  3. 이재윤. WNET ver 0.4.1 프로그램 [cited 2017. 10. 7.] (Lee, Jae-Yun. WNET ver 0.4.1 Software. [cited 2017. 10. 7.])
  4. 정선영, 정은경. 2014. 이미지 감정색인을 위한 시각적 요인 분석에 관한 탐색적 연구. 한국문헌정보학회지, 48(1): 53-73. (Chung, SunYoung and Chung, EunKyung. 2014. "An Exploratory Investigation on Visual Cues for Emotional Indexing of Image." Journal of the Korean Society for Library and Information Science, 48(1): 53-73.) https://doi.org/10.4275/KSLIS.2014.48.1.053
  5. 정은경. 2014. 이용자 반응 기반 이미지 감정 접근점 확장에 관한 연구. 한국비블리아학회지, 25(3): 101-118. (Chung, EunKyung. 2014. "An Expansion of Affective Image Access Points Based on Users' Response on Image." The Korean Biblia Society For Library and Information Science, 25(3): 101-118.) https://doi.org/10.14699/KBIBLIA.2014.25.3.101
  6. Chang, S. L. and Lee, Y. 2001. "Conceptualizing Context and Its Relationship to the Information Behaviour in Dissertation Research Process." The New Review of Information Behavior Research, 2(November): 29-46.
  7. Choi, Y. 2010. "Effects of Contextual Factors on Image Searching on the Web." Journal of the American Society for Information Science and Technology, 61(10): 2011-2028. https://doi.org/10.1002/asi.21386
  8. Chung, E. and Yoon, J. 2009. "Categorical and Specificity Differences between User-supplied Tags and Search Query Terms for Images. An Analysis of Flickr Tags and Web Image Search Queries." Information Research: An International Electronic Journal, 14(3): 403-430.
  9. Chung, E. and Yoon, J. 2011. "Image Needs in the Context of Image Use: An Exploratory Study." Journal of Information Science, 37(2): 163-177. https://doi.org/10.1177/0165551511400951
  10. Chung, E. and Yoon, J. 2013. "An Analysis of Image Use in Twitter Message." Journal of the Korean Biblia Society for Library and Information Science, 24(4): 75-90. https://doi.org/10.14699/kbiblia.2013.24.4.075
  11. Connis, L. R., Ashford, A. J. and Graham, M. E. 2002. "Information Seeking Behavior in Image Retrieval: VISOR I Final Report." Art Libraries Journal, 27(2): 46-47.
  12. Coutright, C. 2007. "Context in Information Behavior Research." The Annual Review of Information Science and Technology, 41(1): 273-306. https://doi.org/10.1002/aris.2007.1440410113
  13. Fidel, R. 1997. "The Image Retrieval Task: Implications for the Design and Evaluation of Image Databases." The New Review Hypermedia and Multimedia, 3: 181-200. https://doi.org/10.1080/13614569708914689
  14. Johnson, J. D. 2003. "On Contexts of Information Seeking." Information Processing and Management, 39: 735-760. https://doi.org/10.1016/S0306-4573(02)00030-4
  15. Knautz, K. and Stock, W. G. 2011. "Collective Indexing of Emotions in Videos." Journal of Documentation, 67(6): 975-994. https://doi.org/10.1108/00220411111183555
  16. Matusiak, K. K. 2006. "Towards User-centered Indexing in Digital Image Collections." OCLC Systems & Services: International Digital Library Perspectives, 22(4): 283-298. https://doi.org/10.1108/10650750610706998
  17. McCay-Peet, L. and Toms, E. 2009. "Image Use within the Work Task Model: Images as Information and Illustration." Journal of the American Society for Information Science and Technology, 60(12): 2416-2429. https://doi.org/10.1002/asi.21202
  18. Menard, E. and Smithglass, M. 2012. "Digital Image Description: a Review of Best Practices in Cultural Institutions." Library Hi Tech, 30(2): 291-309. https://doi.org/10.1108/07378831211239960
  19. Rho, S. and Yeo, S. S. 2013. "Bridging the Semantic Gap in Multimedia Emotion/Mood Recognition for Ubiquitous Computing Environment." The Journal of Supercomputing, 65(1): 274-286. https://doi.org/10.1007/s11227-010-0447-6
  20. Rorissa, A. 2008. "User-generated Descriptions of Individual Images versus Labels of Groups of Images: A Comparison using Basic Level Theory." Information Processing & Management, 44(5): 1741-1753. https://doi.org/10.1016/j.ipm.2008.03.004
  21. Rorissa, A. 2010. "A Comparative Study of Flickr Tags and Index Terms in a General Image Collection." Journal of the American Society for Information Science and Technology, 61(11): 2230-2242. https://doi.org/10.1002/asi.21401
  22. St. Jean, B. et al. 2012. "An Analysis of the Information Behavior, Goals, and Intentions of Frequent Internet Users: Findings from Online Activity Diaries." First Monday, 17(2). [online] [cited 2017. 10. 5.]
  23. Stvilia, B., Jorgensen, C. and Wu, S. 2012. "Establishing the Value of Socially-created Metadata to Image Indexing." Library and Information Science Research, 34(2): 99-109. https://doi.org/10.1016/j.lisr.2011.07.011
  24. Tao, J. and Tan, T. 2005. "Affective Computing: A Review." Quoted in Tao, J., Tan, T. and Picard R.W. eds. 2005. "Affective Computing and Intelligent Interaction." In Proceedings of the 1st International Conference, ACII 2005, Beijing, October 22-24, 2005, Beijing. Heidelberg: Springer-Verlag.
  25. Westman, S. and Oittinen, P. 2006. "Image Retrieval by End-users and Intermediaries in a Journalistic Work Context." In Proceedings of the 1st International Conference on Information Interaction in Context, October 18-20, 2006, Copenhagen: 102-110.
  26. Yoon, J. 2006. "An Exploration of Needs for Connotative Messages during Image Search Process." Proceedings of the Association for Information Science and Technology, 43(1): 1-19.
  27. Yoon, J. and O'Connor, B. 2010. "Engineering an Image-browsing Environment: Re-purposing Existing Denotative Descriptors." Journal of Documentation, 66(5): 750-774. https://doi.org/10.1108/00220411011066826