Alsatian Theater: Computational Drama Analysis with Scarce and Unnormalized Electronic Text

Alsatian theater: Computational drama analysis with scarce and unnormalized electronic text Pablo Ruiz Fabo Université de Strasbourg · UR 1339 LiLPa Colloquium · IDH · Cologne · May 2024 Outline ●Scientific context ○Large-scale analysis of cultural products ○Literary polysystems ●Digitally underrepresented traditions: Alsatian ○Automatic corpus encoding ○Knowledge engineering for metadata representation ○Analysis of non-standardized text: Handling variation ●Resource sharing Culturomics (2010) The “million books” trope (2013) 5 (2013) 6 (2018) (2019) 8 Large scale analysis of cultural products ●Relies on large (textual) corpora ●Subcorpus characterization ○Period, author group ●Based on concrete linguistic or structural traits ○Automatic annotation ○Quantitative analysis ●(For some people) complements close reading 9 Emotion analysis 16 Dennerlein et al (2022) Schmidt et al. (2019) 17 Macroanalysis of theater texts (French) ●French classical theater (Schöch, 2017) ●Subgenre characterization based on LDE topic models 18 Macroanalysis of theater texts (French) 19 (2017) ●Special issue of Revue d’Historiographie du Théâtre 20 2021 21 2024 (soon) DraCor(Drama Corpora) : multilingual platform Fischer et al. (2019) 22 Situation for the most commonly studied traditions 23 Outline ●Scientific context ○Large-scale analysis of cultural products ○Literary polysystems ●Digitally underrepresented traditions: Alsatian ○Automatic corpus encoding ○Knowledge engineering for metadata representation ○Analysis of non-standardized text: Handling variation ●Resource sharing ●Proposed by Even-Zohar (1990) ●Method pays attention to ○Interaction between a core literary tradition and peripheral or emerging ones ○Canon formation practices 25 Literary polysystems 32 33 Several challenges ●No previous electronic text collections for Alsatian theater ○MeThAL project first effort in this direction, covering 1870-1940 period ●No standard orthography for Alsatian varieties ○Statistical analyses requiring a common vocabulary across corpus documents hindered ●NLP resources limited ○But under construction (cf. DIVITAL and RESTAURE projects) 34 Benefits? ●Computational Literary Studies (CLS) ○New material, possibility to compare with results for “larger” traditions ●NLP ○Stimulate methods for small unstandardized, “code-switched” corpora ●More widely ○Promote vitality of language varieties involved 35 36 MeThAL project Goals ●Large electronic corpus creation and quantitative analysis to complement existing knowledge of the Alsatian theater tradition ●Linguistic resources for the analysis of the corpus Corpus creation: Play selection ●Target: 50 plays (>500,000 tokens), 1870-1940 ●Preferred digitized sources (Ca. 250 plays at National Library Strasbourg) ●Preferred plays unanimously considered important in secondary literature ●Variety: ○Genres: comedy must predominate, but also include serious plays and tales ○Author origins and publishers ○Decades covered ○Author status (established or lesser know) ○Male/female authors 37 Corpus creation: Encoding ●TEI format (Text Encoding Initiative) ●Structural divisions ●Detailed bibliographic metadata ●Social variables to describe characters (TEI prosopography) 38 TEI Encoding Recommandations de la Text Encoding Initiative (TEI) 39 40 Source for our TEI versions: Image-mode digitizations by Bnu (National library in Strasbourg) TEI : Bibliographic metadata 41 TEI-encoded data volume Starting from no electronic text: OCR + correction + TEI encoding Based on Wikisource: Rule-based wiki-markup to TEI conversion of the complete works of a single author (August Lustig) Plays Text Tokens TEI released with DOI on data repositories 37 385,441 TEI released (no DOI yet) 14 102,261 Subtotal 51 487,701 Plays Text Tokens TEI released (no DOI yet) 26 136,275 Outline ●Scientific context ○Large-scale analysis of cultural products ○Literary polysystems ●Digitally underrepresented traditions: Alsatian ○Automatic corpus encoding ○Knowledge engineering for metadata representation ○Analysis of non-standardized text: Handling variation ●Resource sharing TEI encoding workflow 50 TEI encoding workflow 51 TEI encoding workflow 52 Corpus creation: TEI encoding PLAYS’ BODY ●Initial 7 plays with rule-based methods ●Based on them (and their OCR), trained Conditional Random Fields to predict: ○act/scene ○stage direction ○speaker name ○speaker’s text ○verse line ●Performance ≥ 0.89 F1 for all classes ●Small training set (largest class 100K) ●Manual correction follows prediction 53 FRONTMATTER ●Too much variability for automation ●Manual transcription of ○Bibliographic metadata ○Dramatis personæ First, we OCR plays. Based on OCR output (after its manual correction) TEI 54 Crédits: Andrew Briand OCR to TEI Océrisation 55 Credits: Andrew Briand OCR to TEI Océrisation 56 Credits: Andrew Briand OCR to TEI OCR to TEI: Rule-based methods ●Rules defined on the basis of ○Lexical triggers ○Typographical and layout information (bounding boxes in OCR output) 57 64 github.com/methal-project/FETE Outline ●Scientific context ○Large-scale analysis of cultural products ○Literary polysystems ●Digitally underrepresented traditions: Alsatian ○Automatic corpus encoding ○Knowledge engineering for metadata representation ○Analysis of non-standardized text: Handling variation ●Resource sharing TEI encoding workflow 66 Character lists provide a sociobiographic and dramatic overview (Wiedmer et al., 2020 i.a.) 67 Ruiz & Werner (2021) Character social variable annotation ●Links with earlier studies on the tradition, which have focused on the plays’ “social picture” ●Annotating dramatis personæ is a feasible effort while text is still under encoding ●It can give an overview of social groups in the plays and their evolution ○Allows us to find plays where these groups interact ○Can help predict conflicts depicted 68 Character social variable annotation ●Annotated profession, professional group, class, gender, age ○Missing: origin and languages ●Characteriseme taxonomy (cf. Galleron, 2017) with mimetic features (Phelan, 1989) ●TEI feature structures 69 Transcription et annotation des personnages 70 Socioprofessional groups ●12 groups ○professionals, scientific, technical ○intermediate professions ○service and sales ○crafts ○industry and transportation ○agriculture 71 ○elementary professions ○rentiers ○clergy ○military ○government officials ○associative world ●Inspired by historical profession taxonomies like HISCO (van Leeuwen et al., 2014) Ruiz & Werner (2021) 72 f general fs mimetic fsdDecl character_specification fs synthetic f socio_economic_status f relation_position f language fs professional _activities fs socio_economic _other fs relation_type f professional _category f occupation f social_class f family f status_cerf f personal f professional fs general_features 73 f general fs mimetic fsdDecl character_specification fs synthetic f socio_economic_status f relation_position f language fs professional _activities fs socio_economic _other fs relation_type f professional _category f occupation f social_class f family f status_cerf f personal f professional fs general_features <person xml:id="mtl-per-0890"> <bibl corresp="#mtl-090"/> <persName>Alice Sandel</persName> <note type="roleDesc">Dactylo</note> <occupation>Dactylo</occupation> <fs type="character_specification"> <f name="specification_type"> <fs type="mimetic_features"> <f name="general"> <fs type="general_features"> <f name="sex"><symbol value="F"/></f> </fs> </f> <f name="socio_economic_status"> <vColl> <fs type="professional_activities"> <f name="occupation"> <symbol value="typist"/> </f> <f name="professional_category"> <symbol value="intermediate_professionals"/> </f> </fs> <fs type="socio_economic_other"> <f name="social_class"> <symbol value="lower_class"/> </f> </fs> </vColl> </f> <f name="language"> <default/> </f> </fs> </f> </fs> </person> <person xml:id="mtl-per-0890"> <bibl corresp="#mtl-090"/> <persName>Alice Sandel</persName> <note type="roleDesc">Dactylo</note> <occupation>Dactylo</occupation> <fs type="character_specification"> <f name="specification_type"> <fs type="mimetic_features"> <f name="general"> <fs type="general_features"> <f name="sex"><symbol value="F"/></f> </fs> </f> <f name="socio_economic_status"> <vColl> <fs type="professional_activities"> <f name="occupation"> <symbol value="typist"/> </f> <f name="professional_category"> <symbol value="intermediate_professionals"/> </f> </fs> <fs type="socio_economic_other"> <f name="social_class"> <symbol value="lower_class"/> </f> </fs> </vColl> </f> <f name="language"> <default/> </f> </fs> </f> </fs> </person> <person xml:id="mtl-per-0890"> <bibl corresp="#mtl-090"/> <persName>Alice Sandel</persName> <note type="roleDesc">Dactylo</note> <occupation>Dactylo</occupation> <fs type="character_specification"> <f name="specification_type"> <fs type="mimetic_features"> <f name="general"> <fs type="general_features"> <f name="sex"><symbol value="F"/></f> </fs> </f> <f name="socio_economic_status"> <vColl> <fs type="professional_activities"> <f name="occupation"> <symbol value="typist"/> </f> <f name="professional_category"> <symbol value="intermediate_professionals"/> </f> </fs> <fs type="socio_economic_other"> <f name="social_class"> <symbol value="lower_class"/> </f> </fs> </vColl> </f> <f name="language"> <default/> </f> </fs> </f> </fs> </person> TEI personography: Data volume ●Plays: 231 ●Characters: 2,386 ●Professions: Vocabulary with 350 unique professions (divided into 12 groups) 83 84 Group evolution: High-change groups 85 Group evolution: Stable groups 86 Group evolution: Stable groups 87 Group evolution: Discontinuous groups 88 Group evolution: Female characters Character gender distribution 89 96 Social groups and subgenre: Professional category Limitations: Characters without social metadata? 97 Outline ●Scientific context ○Large-scale analysis of cultural products ○Core and periphery ●Digitally underrepresented traditions: Alsatian ○Automatic corpus encoding ○Knowledge engineering for metadata representation ○Analysis of non-standardized text: Handling variation ●Resource sharing What about text-based analyses? ELAL: An Emotion Lexicon for the Analysis of Alsatian Theatre Plays ●Text-based analyses require handling scriptolinguistic variation ●ELAL (work by Delphine Bernhard, 2022) ○Creating an emotion lexicon that handles variation ○Based on French-Alsatian bilingual lexica ○Based on existing emotion lexica for French and German ■FEEL (Abdaoui et al, 2017) ■NRC lexica (Mohammad, 2020) ●All source lexica are aggregated into a large network ●Variants are identified with string similarity + the double metaphone algorithm 99 What about text-based analyses? ELAL: An Emotion Lexicon for the Analysis of Alsatian Theatre Plays ●Manual correction to detect incorrect variants ●Lexicon: 3,273 entries ▫ 11,920 Alsatian forms ▫ 3.64 variants/entry Delphine Bernhard (2022) 100 What about text-based analyses? ELAL: An Emotion Lexicon for the Analysis of Alsatian Theatre Plays Bernhard (2022) 101 doi.org/10.34847/nkl.40cex998 Results ●Best model overall: Ridge Classifier, using all the features. ●DeezyMatch (deep learning, Coll et al., 2020) obtains slightly lower results (due to the amount of training data?) (experiments by Bernhard, 2022) 102 103 Potential use: Variant-based search EDYTHA: Emotion DYnamics in THeater in Alsatian ●Applies ELAL lexicon to determine emotion evolution patterns in ●Based on Tweet Emotion Dynamics tool (Vishnubhotla & Mohammad 2022) ●Main developer: Qinyue Liu ●Configurable term-weighting schemes to give more importance to emotion terms that are discriminative in a given text-unit ○tf-idf weights, with idf per play ○tf-idf weights, with idf per speech turn 104 EDYTHA: Emotion dynamics in theater in Alsatian ●Sanity check: positive correlation between anger and fear negative correlation between anger and joy 105 112 113 114 115 116 117 Conclusion 118 Conclusion 119 Conclusion ●The rich Computational Literary Studies results available for major literary traditions will be possible for lesser studied ones ●A lot of effort is needed to create the resources that enable such results ●As more NLP becomes available for Alsatian varieties—cf. corpora developed in DIVITAL (Bernhard et al., 2022), the range of CLS questions we can address will increase ●Metadata-based studies a possibility when other resources are lacking 120 Newer project ●Comparison is based on character lists, play settings, song names + bibliographic metadata ●Assess influence of German and French popular genres on Alsatian theater ●We will attempt to represent plays as feature vectors and apply similarity metrics 121 128 Andresen, M., Krautter, B., Pagel, J., & Reiter, N. (2024). Knowledge Distribution in German Drama. Journal of Open Humanities Data, 10(1). https://doi.org/10.5334/johd.167 Bernhard, D. & Ruiz, P. (2022). ELAL: An emotion lexicon for the analysis of Alsatian theatre plays. Proceedings on the Conference on Language Resources and Evaluation (LREC 2022), 5001-5010 Cerf, E. (1972). Le théâtre alsacien de Strasbourg, miroir d’une société (1898-1939). Saisons d’Alsace, 43. Cerf, E. (1975). Les contes merveilleux du Théâtre alsacien de Strasbourg. Revue des sciences sociales de la France de l’Est, 4, 3-30 Coll Ardanuy, Mariona, Kasra Hosseini, Katherine McDonough, Amrey Krause, Daniel van Strien, and Federico Nanni. 2020. A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching. Technical report arXiv:2009.08114. ArXiv:2009.08114 [cs] type: article. arXiv, September. Dennerlein, K., Schmidt, T., & Wolff, C. (2022). Emotionen im kulturellen Gedächtnis bewahren. DHd 2022 Kulturen des digitalen Gedächtnisses. Potsdam. Zenodo. https://doi.org/10.5281/zenodo.6327957 Dilan Canan, Ç. & Fischer, F. (2022). Dramatische Metadaten. Die Datenbank deutschsprachiger Einakter 1740-1850. In DHd2022: Kulturen des digitalen Gedächtnisses. University of Potsdam. Fischer, F, Börner, I., Göbel, M., Hechtl, A., Kittel, C, Milling, C, Trilcke, P. (2019). Programmable Corpora: Introducing DraCor, an Infrastructure for the Research on European Drama. Proceedings of Digital Humanities 2019. Gall. J.-M. (1974). Le théâtre populaire alsacien au XIXe siècle. Istra Galleron, I. (Ed.). (2017). Revue d’Historiographie du Théâtre, Numéro 4: Études théâtrales et humanités numériques. Galleron, I. (2017). Conceptualisation of Theatrical Characters in the Digital Paradigm : Needs, Problems and Foreseen Solutions. Human and Social Studies, 6(1), 88‑108. https://doi.org/10.1515/hssr-2017-0007 Huck, D. (1898). D’r Herr Maire (1898) de Gustave Stoskopf. Entre ethnologie et littérature: Les Alsaciens an auto-représentation. Recherches Germaniques, 28, 163-190 Huck, D. (2005). Le «Théâtre Alsacien de Strasbourg» et la production dramaturgique de ses fondateurs (1898-1914). In J.-M. Leveratto, J. Benay, O. Thomas, & S. Wuttke, Culture et histoire des spectacles en Alsace et en Lorraine : De l’annexion à la décentralisation (1871-1946) (p. 198‑222). Peter Lang. Huck, D. (2015). Une histoire des langues de l’Alsace. La Nuée Bleue. Huck, D., Bothorel-Witz, A., & Geiger-Jallet, A. (2007). L’Alsace et ses langues. Eléments de description d’une situation sociolinguistique en zone frontalière. In A. Abel et al. (Éds.), Aspects of Multilingualism in European Border Regions : Insights and Views from Alsace, Eastern Macedonia and Thrace, the Lublin Voivodeship and South Tyrol (p. 13‑101). EURAC Research 129 References Hülsen, B. von. (2003). Szenenwechsel im Elsass : Theater und Gesellschaft in Strassburg zwischen Deutschland und Frankreich 1890-1944. Leipziger Universitätsverlag. Moeller, K., & Nasarek, R. (2018). Die Ontologie historischer deutschprachiger Berufsund Amtsbezeichnungen. Interoperationalität und Berufsklassifizierung durch semantisches Topic Modeling. DHd 2018. Kritik der Digitalen Vernunft. Phelan, James. 1989. Reading People, Reading Plots: Character, Progression, and the Interpretation of Narrative. Chicago: University of Chicago Press. Reiter, N. (2020). Möglichkeiten Quantitativer Dramenanalyse. Comparatio. Zeitschrift für Vergleichende Literaturwissenschaft, 12(2), 39–52. https://doi.org/10.1007/978-3-476-04516-4_16 Ruiz Fabo, P., Bernhard, D., & Werner, C. (2020). Création d’un corpus FAIR de théâtre en alsacien et normalisation de variétés non-contemporaines. In T. Poibeau, Y. Parmentier, & E. Schang (Eds.), 2èmes journées scientifiques du Groupement de Recherche Linguistique Informatique Formelle et de Terrain (LIFT) (pp. 34–43). CNRS. Ruiz Fabo, P., & Werner, C. (2021). Exploration du théâtre alsacien à travers ses listes de personnages pendant la période 1870-1940. Humanistica 2021. Humanistica 2021, Rennes (online). https://doi.org/10.5281/zenodo.4762733 Schmidt, T., Burghardt, M., Dennerlein, K., & Wolff, C. (2019). Katharsis – A Tool for Computational Drametrics. Digital Humanities 2019. Digital Humanities 2019, Utrecht, The Netherlands. https://dev.clariah.nl/files/dh2019/boa/0584.html Van Leeuwen, M. H. D., Maas, I., & Miles, A. (2004). Creating a Historical International Standard Classification of Occupations An Exercise in Multinational Interdisciplinary Cooperation. Historical Methods: A Journal of Quantitative and Interdisciplinary History, 37(4), 186‑197. https://doi.org/10.3200/HMTS.37.4.186-197 Wiedmer, N., Pagel, J., & Reiter, N. (2020). Romeo, Freund des Merkutio : Semi-Automatische Extraktion von Beziehungen zwischen dramatischen Figuren. DHd2020 Spielräume. Digital Humanities zwischen Modellierung und Interpretation. Konferenzabstracts., 194‑200. https://doi.org/10.5281/zenodo.3666689 130 References DraCor: https://dracor.org Dramacode: https://github.com/dramacode/ Emotions in Drama: https://dfg-spp-cls.github.io/projects_en/2020/01/24/TP-Emotions_in_Drama/ QuaDramA & Q:TRACK: https://quadrama.github.io/index.en RESTAURE: https://restaure.unistra.fr DIVITAL: https://divital.gitpages.huma-num.fr/ Théâtre classique: http://www.theatre-classique.fr Projects cited Märsi fer ‘s Züheere ! 131 https://methal.pages.unistra.fr/en https://thealtres.pages.unistra.fr This research was supported by University of Strasbourg’s IdEx program and MISHA Special thanks to our interns: Nathanaël Beiner, Fanny Boisnard, Lena Camillone, Hoda Chouaib, Audrey Deck, Enzo Doyen, Barbara Hoff, Valentine Jung, Salomé Klein, Audrey Li-Thiao-Té, Qinyue Liu, Kévin Michoud, Alexia Schneider, Vedisha Toory, Heng Yang Thanks to the project team; resources described here created in collaboration with Delphine Bernhard, Andrew Briand, Qinyue Liu and Carole Werner