기계학습을 이용한 역사 텍스트의 저자판별: 1920년대 개벽 잡지의 논설 텍스트 = Machine Learning-Based Authorship Attribution for Historical Texts – a case study of GaeByeok magazine in the 1920s

다국어 초록 (Multilingual Abstract)

This study aims to demonstrate how the authorship attribution techniques can be appliedto historical texts, exploring the potential of authorship attribution as a solution to the realworld authorship disputes and the possibility of multidisciplinary research that combineshumanities and quantitative text analytics. History and literary studies have used traditionalmethods of judging the similarity of topics and subject matters or relying on extra-textualinformation to solve the authorship problems. This subjective and anecdotal approach toauthorship needs to be complemented by incorporating objective and quantitativemethodology that examines intra-textual clues. As the first case study, we performed machinelearning-based authorship attribution analysis on the 164 opinion texts with unknownauthorship from GaeByeok magazine of the 1920s. To enhance accuracy and reliability ofthe analysis, an improved machine learning algorithm was devised based on SVM byincorporating three parameters α, β, θ into the prediction model. This study is also acase study showing how to perform the authorship attribution analysis in an open setting,not in a closed setting. We hope that the prediction results of the analysis will encourageand facilitate more productive discussion among related disciplines on authorshipidentification and verification of real historical texts.

참고문헌 (Reference)

1 金明哲, "최소거리법과 기계학습법에 의한 한국어 텍스트의 저자 판별" 한국조사연구학회 13 (13): 175-190, 2012

2 김일환, "저자 판별을 위한 전산 문체론 - 초기 현대소설을 대상으로" 국어국문학회 (170) : 207-240, 2015

3 이병태, "소춘 김기전(小春 金起田)의 서구 철학·사상수용 특징- 저술의 분류와 개관에 기초하여 -" 한국철학사상연구회 28 (28): 143-189, 2017

4 한나래, "빈도 정보를 이용한 한국어 저자 판별" 한국인지과학회 20 (20): 225-241, 2009

5 강남준, "독립신문 논설의 형태 주석 말뭉치를 활용한 논설 저자 판별 연구 －어미 사용빈도 분석을 중심으로－" 한국사전학회 (15) : 73-101, 2010

6 최지명, "기계학습 알고리즘을 이용한 한국어 텍스트 저자 판별: 블로그의 영화 리뷰를대상으로" 연세대학교 대학원 2015

7 정용서, "개벽사의 잡지 발행과 편집진의 역할" 한국민족운동사학회 (83) : 145-186, 2015

8 이승윤, "『삼천리』에 나타난 역사기획물의 특징과 잡지의 방향성" 인문학연구원 (46) : 457-480, 2013

9 허수, "『개벽』의 종교적 사회운동론과 일본의 ‘종교철학’" 인문학연구원 72 (72): 325-355, 2015

10 조규태, "『개벽』을 이끈 사람들" 2007

11 최수일, "『개벽』연구" 소명출판 2008

12 김정순, "《開闢》誌의 雜誌史的 價値 硏究" 출판문화학회 9 (9): 154-165, 2001

13 Burrows, J., "‘Delta’: a measure of stylistic difference and a guide to likely authorship" 17 (17): 267-287, 2002

14 Binongo, J.N.G., "Who wrote the 15th book of Oz? An application of multivariate analysis to authorship attribution" 16 (16): 9-17, 2003

15 Fung, G., "The disputed Federalist Papers: SVM feature selection via concave minimization" ACM 42-46, 2003

16 Joachims, T., "Text categorization with support vector machines: Learning with many relevant features" 137-142, 1998

17 Bosch, R.A., "Separating hyperplanes and the authorship of the disputed federalist papers" 105 (105): 601-608, 1998

18 Grieve, J., "Quantitative authorship attribution: An evaluation of techniques" 22 (22): 251-270, 2007

19 Yule, G.U., "On sentence-length as a statistical characteristic of style in prose: With application to two cases of disputed authorship" 30 (30): 363-390, 1939

20 Wang, L. Z., "News authorship identification with deep learning"

21 Kešelj, V., "N-gram-based author profiles for authorship attribution" 3 : 255-264, 2003

22 Brinegar, C.S., "Mark Twain and the Quintus Curtius Snodgrass letters: A statistical test of authorship" 58 (58): 85-96, 1963

23 Labbé, C., "Inter-textual distance and authorship attribution Corneille and Molière" 8 (8): 213-231, 2001

24 Mosteller, F., "Inference and disputed authorship: The Federalist" 1964

25 Dumais, S., "Inductive learning algorithms and representations for text categorization" ACM 148-155, 1998

26 Tweedie, F.J., "How variable may a constant be? Measures of lexical richness in perspective" 32 (32): 323-352, 1998

27 Shrestha, P., "Convolutional Neural Networks for Authorship Attribution of Short Texts" 669-, 2017

28 Koppel, M., "Computational methods in authorship attribution" 60 (60): 9-26, 2009

29 Hirst, G., "Bigrams of syntactic labels for authorship discrimination of short texts" 22 (22): 405-417, 2007

30 Ebrahimpour, M., "Automated authorship attribution using advanced signal classification techniques" 8 (8): e54998-, 2013

31 Diederich, J., "Authorship attribution with support vector machines" 19 (19): 109-123, 2003

32 Stamatatos, E., "Authorship attribution using text distortion" 1 : 1138-1149, 2017

33 Mohan, A., "Authorship attribution of SMS messages using an N-grams approach" 2010

34 Koppel, M., "Authorship attribution in the wild" 45 (45): 83-94, 2011

35 Mikros, G.K., "Authorship attribution and gender identification in Greek Blogs" 21 : 21-32, 2012

36 Holmes, D.I., "Authorship attribution" 28 (28): 87-106, 1994

37 Juola, P., "Authorship attribution" 1 (1): 233-334, 2008

38 Houvardas, J., "Artificial Intelligence: Methodology, Systems, and Applications" 77-86, 2006

39 Juola, P., "A prototype for authorship attribution studies" 21 (21): 169-178, 2006

40 Zheng, R., "A framework for authorship identification of online messages : Writing‐style features and classification techniques" 57 (57): 378-393, 2006

41 Jockers, M.L., "A comparative study of machine learning methods for authorship attribution" 25 (25): 215-223, 2010

42 김정인, "<<개벽>>을 낳은 현실, <<개벽>>에 담긴 희망" 한국역사연구회 (57) : 21-48, 2005

43 강명희, "20세기 전반기 한국 자유주의의 형성과 굴절" 인문학연구원 71 (71): 229-267, 2014

44 정용서, "1930년대 개벽사 발간 잡지의 편집자들" 역사실학회 (57) : 225-260, 2015

45 허수, "1920년대 『개벽』의 정치사상-‘범인간적 민족주의’를 중심으로-" 한국학중앙연구원 31 (31): 305-331, 2008