딥러닝 기반 영화 인물들 간의 상관관계 분석
Analyzing Correlations between Movie Characters Based on Deep Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
인간은 사회적인 동물로서, 대화로써 정보를 얻거나 사회적인 교류를 해왔다. 대화는 두 사람 이상의작은 모임에서 서로 말을 편하게 주고받는 것으로, 한 사람이 다른 사람에게 가지는 감성에 따라 그말의 분위기가 달라질 수 있다. 영화에서 인물들과 인물들이 펼치는 이야기는 중요한 요소로 작용하며, 인물들 간의 관계는 이야기와 인물 간의 대사를 이해하는데 꼭 필요하다. 그러나 이런 정보를 영화에서자동으로 추출하는 방법은 아직까지 연구되지 않아서 관객들에게 제공되고 있지 못하고 있다. 따라서, 영화 속 양상을 자동으로 분석하는 모델이 필요하다. 본 논문에서는 딥 러닝 기법을 활용하여 각 영화등장 인물들 간의 감성을 측정하여 영화 속 인물들 간의 관계를 효과적으로 분석하는 방법을 제안한다. 제안 방법은 먼저 영화 대본으로부터 주요 인물들을 추출하고, 주요 인물들 간의 대화를 효과적으로찾는다. 그런 다음, 주요 인물들 간의 관계를 분석하기 위하여, 감성 분석을 수행하여 전체 시간 간격내 대사의 위치에 따라 가중치를 부여하고 점수를 수집한다. 또한, 실데이터를 이용한 실험을 통하여제안 기법이 효과적으로 영화 등장 인물들 간의 감성을 분석할 수 있음을 보인다.
Abstract
Humans are social animals that have gained information or social interaction through dialogue. In conversation, the mood of the word can change depending on the sensibility of one person to another. Relationships between characters in films are essential for understanding stories and lines between characters, but methods to extract this information from films have not been investigated. Therefore, we need a model that automatically analyzes the relationship aspects in the movie. In this paper, we propose a method to analyze the relationship between characters in the movie by utilizing deep learning techniques to measure the emotion of each character pair. The proposed method first extracts main characters from the movie script and finds the dialogue between the main characters. Then, to analyze the relationship between the main characters, it performs a sentiment analysis, weights them according to the positions of the metabolites in the entire time intervals and gathers their scores. Experimental results with real data sets demonstrate that the proposed scheme is able to effectively measure the emotional relationship between the main characters.
참고문헌 (26)
- Yaakub, "A Review on Sentiment Analysis Techniques and Applications", IOP Conf. Series: Materials Science and Engineering (2019)[DOI]
- James A. Russell, "A circumplex model of affect.", Journal of Personality and Social Psychology, 39(6), pp.1161~1178 (1980), American Psychological Association (APA)[DOI]
- Ian David, "Screenwriting and emotional rhythm", Journal of Screenwriting, 5(1), pp.47~57 (2014), Intellect[DOI]
- "IMDb"[URL]
- Hutto, "VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text", ICWSM proceedings (2015)
- NRC Emotion Lexicon, "Mohammad", National Research Council, Canada, ~ (2013)
- 유혜연, "Emotion and Sentiment Analysis from a Film Script: A Case Study", 디지털콘텐츠학회논문지, 18(8), pp.1537~1542 (2017), 한국디지털콘텐츠학회[DOI]
- Yasen, "Movies Reviews Sentiment Analysis and Classification", Conference: 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT) (2019)
- V Uma Ramya, "Sentiment Analysis of Movie Review using Machine Learning Techniques", International Journal of Engineering & Technology, 7(2.7), pp.676~ (2018), Science Publishing Corporation[DOI]
- Palak Baid, "Sentiment Analysis of Movie Reviews using Machine Learning Techniques", International Journal of Computer Applications, 179(7), pp.45~49 (2017), Foundation of Computer Science[DOI]
- Lee, "Analyzing Movie Scripts as Unstructured Text", 2017 IEEE Third International Conference on Big Data Computing Service and Applications (BigDataService) (2017)
- A. Esuli, "SENTI-WORDNET: A Publicly Available Lexical Resource for Opinion Mining", Proc. of the 5th Conf. on Language Resources and Evaluation (LREC’06), 2006, pp.417~422 (2006)
- Francis, M.E., "Linguistic Inquiry and Word Count" (1993), Southern Methodist University
- William S. Cleveland, "Robust Locally Weighted Regression and Smoothing Scatterplots", Journal of the American Statistical Association, 74(368), pp.829~836 (1979)
- Abraham. Savitzky, "Smoothing and Differentiation of Data by Simplified Least Squares Procedures.", Analytical Chemistry, 36(8), pp.1627~1639 (1964), American Chemical Society (ACS)[DOI]
- R.A. Haddad, "A class of fast Gaussian binomial filters for speech and image processing", IEEE Transactions on Signal Processing, 39(3), pp.723~727 (1991), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- V. Devisree, "A Hybrid Approach to Relationship Extraction from Stories", Procedia Technology, 24, pp.1499~1506 (2016), Elsevier BV[DOI]
- Jessica L. Lakin, "The chameleon effect as social glue: Evidence for theevolutionary significance of nonconscious mimicry", Journal of Nonverbal Behavior, 27(3), pp.145~162 (2003), Springer Science and Business Media LLC[DOI]
- Danescu-Niculescu-Mizil, "Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs", ACL (2011)
- Francis, M.E, "Linguistic Inquiry and Word Count" (1993), Southern Methodist University
- "IMSDb"[URL]
- "BeautifulSoup"[URL]
- Halteren, "Writing Style Recognition and Sentence Extraction", Proceedings of the workshop on automatic summarization, pp.66~70 (2002)
- Molly E. Ireland, "Language Style Matching Predicts Relationship Initiation and Stability", Psychological Science, 22(1), pp.39~44 (2011), SAGE Publications[DOI]
- "Kaggle"[URL]
- Syd Field, "The Foundations of Screenwriting" (1979), Dell Publishing Company