Gender classification in classical fiction: A computational analysis of 1113 fictions

Dan Zhu; Liru Yang; Xin Liang; Dan Zhu; Liru Yang; Xin Liang

doi:10.3934/mbe.2022412

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 9: 8892-8907. doi: 10.3934/mbe.2022412

Previous Article Next Article

Research article Special Issues

Gender classification in classical fiction: A computational analysis of 1113 fictions

1.
School of Foreign Languages, South China University of Technology, Guangzhou 510641, China
2.
School of Mathematics, South China University of Technology, Guangzhou 510641, China

Academic Editor: Weining Wu

Received: 02 May 2022 Revised: 29 May 2022 Accepted: 06 June 2022 Published: 20 June 2022

Recent decades have witnessed the rapid development of literary studies on gender and writing style. One of the common limitations of previous studies is that they analyze only a few texts, which some researchers have already pointed out. In this study, we attempt to find the features that best facilitate the classification of texts by authorial gender. Based on a corpus of 1113 classical fictions from the early 19^th century to the early 20^th century. Eight algorithms, including SVM, random forest, decision tree, AdaBoost, logistic regression, K-nearest neighbors, gradient boosting and XGBoost, are used to automatically select the features that are most useful for properly categorizing a text. We find that word frequency is the most important predictor for identifying authorial gender in classical fictions, achieving an accuracy rate of 92%. We also find that nationhood is not particularly impactful when dealing with authorial gender differences in classical fictions, as genderlectal variation is 'universal' in the English-speaking world.
- authorial gender,
- gender classification,
- genderlectal,
- machine learning,
- classical literature,
- word frequency,
- lexical features,
- logistic regression
Citation: Dan Zhu, Liru Yang, Xin Liang. Gender classification in classical fiction: A computational analysis of 1113 fictions[J]. Mathematical Biosciences and Engineering, 2022, 19(9): 8892-8907. doi: 10.3934/mbe.2022412

Related Papers:

Abstract

Recent decades have witnessed the rapid development of literary studies on gender and writing style. One of the common limitations of previous studies is that they analyze only a few texts, which some researchers have already pointed out. In this study, we attempt to find the features that best facilitate the classification of texts by authorial gender. Based on a corpus of 1113 classical fictions from the early 19^th century to the early 20^th century. Eight algorithms, including SVM, random forest, decision tree, AdaBoost, logistic regression, K-nearest neighbors, gradient boosting and XGBoost, are used to automatically select the features that are most useful for properly categorizing a text. We find that word frequency is the most important predictor for identifying authorial gender in classical fictions, achieving an accuracy rate of 92%. We also find that nationhood is not particularly impactful when dealing with authorial gender differences in classical fictions, as genderlectal variation is 'universal' in the English-speaking world.

References

[1]	R. Lakoff, Language and woman's place, Lang. Soc., 2 (1973), 45–79. https://doi.org/10.1017/S0047404500000051 doi: 10.1017/S0047404500000051
[2]	J. Holmes, Women's talk: The question of sociolinguistic universals, Aust. J. Commun., 20 (1993), 125–149. https://doi.org/10.5588/pha.15.0018 doi: 10.5588/pha.15.0018
[3]	E. J. Aries, F. L. Johnson, Close friendship in adulthood: Conversational content between same-sex friends, Sex Roles, 9 (1983), 1183–1196. https://doi.org/10.1007/bf00303101 doi: 10.1007/bf00303101
[4]	D. Tannen, Rethinking power and solidarity in gender and dominance, in Proceedings of the Annual Meeting of the Berkeley Linguistics Society, 16 (1990), 519. https://doi.org/10.3765/bls.v16i1.3433
[5]	J. Holmes, Women's language: A functional approach, Gen. Ling., 24 (1984), 149.
[6]	J. Holmes, Paying compliments: A sex-preferential positive politeness strategy, J. Pragmatics, 12 (1988), 445–465. https://doi.org/10.1016/0378-2166(88)90005-7 doi: 10.1016/0378-2166(88)90005-7
[7]	J. Holmes, Sex differences and apologies: One aspect of communicative competence, Appl. Ling., 10 (1989), 194–213. https://doi.org/10.1093/applin/10.2.194 doi: 10.1093/applin/10.2.194
[8]	C. L. Berryman-Fink, J. R. Wilcox, A multivariate investigation of perceptual attributions concerning gender appropriateness in language, Sex Roles, 9(1983), 663–681. https://doi.org/10.1007/BF00289796 doi: 10.1007/BF00289796
[9]	J. A. Simkins-Bullock, B. G. Wildman, An investigation into the relationship between gender and language, Sex Roles, 24 (1991), 149–160. https://doi.org/10.1007/BF00288888 doi: 10.1007/BF00288888
[10]	S. Argamon, M. Koppel, J. Fine, A. R. Shimoni, Gender, genre, and writing style in formal written texts, Text, 23 (2003), 321–346. https://doi.org/10.1515/text.2003.014 doi: 10.1515/text.2003.014
[11]	J. D. Burger, J. C. Henderson, G. Kim, G. Zarrella, Discriminating gender on twitter, in Conference on Empirical Methods in Natural Language Processing, (2011), 1301–1309. Available from: https://dblp.uni-trier.de/rec/conf/emnlp/BurgerHKZ11.html.
[12]	R. Sarawgi, K. Gajulapalli, Y. Choi, Gender attribution: Tracing stylometric evidence beyond topic and genre, in Proceedings of the Fifteenth Conference on Computational Natural Language Learning, (2011), 78–86. Available from: https://dblp.uni-trier.de/db/conf/conll/conll2011.html.
[13]	M. Dahllöf, Automatic prediction of gender, political affiliation, and age in Swedish politicians from the wording of their speeches—A comparative study of classifiability, Lit. Ling. Comput., 27 (2012), 139–153. https://doi.org/10.1093/llc/fqs010 doi: 10.1093/llc/fqs010
[14]	B. Yu, Language and gender in Congressional speech, Lit, Ling, Comput., 29 (2014), 118–132. https://doi.org/10.1093/llc/fqs073 doi: 10.1093/llc/fqs073
[15]	D. L. Hoover, Textual analysis, in Literary Studies in the Digital Age (eds. K. M. Price and R. Siemens), 2013. Available from: http://dlsanthology.commons.mla.org/textual-analysis/.
[16]	M. L. Newman, C. J. Groom, L. D. Handelman, J. W. Pennebaker, Gender differences in language use: An analysis of 14,000 text samples, Discourse Processes, 45 (2008), 211–236. https://doi.org/10.1080/01638530802073712 doi: 10.1080/01638530802073712
[17]	J. Pennebaker, The Secret Life of Pronouns: What Our Words Say about Us, Bloomsbury Press, London, (2011), 56. https://doi.org/10.1093/llc/fqt006
[18]	P. Baker, Using Corpora to Analyze Gender, Bloomsbury, London, 2014. https://doi.org/10.1016/j.system.2016.04.008
[19]	G. Flaubert, The Letters of Gustave Flaubert, 1830–1857, Harvard University Press, 1980.
[20]	M. Koppel, S. Argamon, A. R. Shimoni, Automatically categorizing written texts by author gender, Lit. Ling. Comput., 17 (2003), 401–412. https://doi.org/10.1093/llc/17.4.401 doi: 10.1093/llc/17.4.401
[21]	M. Jockers, Macroanalysis: Digital Methods and Literary History, University of Illinois Press, Urbana, (2013), 93–99,133. https://doi.org/10.5406/illinois/9780252037528.001.0001
[22]	J. Rybicki, Vive la difference: Tracing the (authorial) gender signal by multivariate analysis of word frequencies, Digital Scholarship Humanit., 31 (2016), 746–761. https://doi.org/10.1093/llc/fqv023 doi: 10.1093/llc/fqv023
[23]	S. G. Weidman, J. O'Sullivan, The limits of distinctive words: Re-evaluating literature's gender marker debate, Digital Scholarship Humanit., 33 (2018), 374–390. https://doi.org/10.1093/llc/fqx017 doi: 10.1093/llc/fqx017
[24]	S. Grayson, M. Mulvany, K. Wade, G. Meaney, D. Greene, Exploring the role of gender in 19th century fiction through the lens of word embeddings, in 1st International Conference on Language, Data and Knowledge, (2017), 358–364. Available from: https://linkspringer.53yu.com/chapter/10.1007/978-3-319-59888-8_30.
[25]	V. Bergvall, Rethinking language and gender research: Theory and practice, J. Pragmatics, 29 (1996), 213–220. https://doi.org/10.1016/S0378-2166(97)82076-0 doi: 10.1016/S0378-2166(97)82076-0
[26]	R. Potter, Literary criticism and literary computing, Comput. Humanit., 22 (1988), 91–97. https://doi.org/10.2307/30200105 doi: 10.2307/30200105
[27]	J, Gottschall, Literature, Science, and a New Humanities, Palgrave Macmillan, New York, 2008. https://doi.org/10.1057/9780230615595
[28]	L. Cassuto, C. V. Eby, B. Reiss, The Cambridge History of the American Novel, Cambridge University Press, 2011. https://doi.org/10.1017/CHOL9780521899079
[29]	J. Bender, D. David, M. Seidel, The Columbia History of the British Novel, Columbia University Press, 1994. https://doi.org/10.2307/3508695
[30]	A. A. Augustine, M. R. Mehl, R. J. Larsen, A positivity bias in written and spoken English and its moderation by personality and gender, Social Psychol. Pers. Sci., 2 (2011), 508–515. https://doi.org/10.1177/1948550611399154 doi: 10.1177/1948550611399154
[31]	S. Luoto, Sexual dimorphism in language, and the gender shift hypothesis of homosexuality, Front. Psychol., 12 (2021), 1665. https://doi.org/10.3389/fpsyg.2021.639887 doi: 10.3389/fpsyg.2021.639887

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)