Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning

Melanie Andresen; Dagmar Knorr

doi:10.18420/inf2020_124

Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning

Melanie Andresen
, Dagmar Knorr

Writing Center

University of Stuttgart

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Abstract

The use of the pronoun ich (‘I’) in academic language is a source of constant debate and a frequent cause of insecurity for students. We explore manually annotated instances of I from a German learner corpus. Using machine learning techniques, we investigate to what extent it is possible to automatically distinguish between different types of I usage (author I vs. narrator I). We additionally inspect which context words are good indicators of one type or the other. The results show that an automatic classification is not straightforward, but the distinctive features are in line with previous research. The results of the automatic classification are not perfect, but would greatly facilitate manual annotation. The distinctive words are in line with previous research and indicate that the author I is a more homogeneous class.

Translated title of the contribution	Erforschung der Verwendung des Pronomen Ich in deutschen akademischen Texten mit maschinellem Lernen
Original language	English
Title of host publication	Informatik 2020 - Back to the future : 50. Jahrestagung der Gesellschaft für Informatik vom 28. September - 2. Oktober 2020, virtual
Editors	Ralf H. Reussner, Anne Koziolek, Robert Heinrich
Number of pages	7
Place of Publication	Bonn
Publisher	Gesellschaft für Informatik e.V.
Publication date	2020
Pages	1327-1333
ISBN (Electronic)	978-3-88579-701-2
DOIs	https://doi.org/10.18420/inf2020_124
Publication status	Published - 2020
Event	50th Annual Conference of the German Informatics Society - INFORMATIK 2020: Back to the Future - Online, Karlsruhe, Germany Duration: 28.09.2020 → 02.10.2020 Conference number: 50 https://informatik2020.gi.de/ https://gi.de/themen/beitrag/politik-in-den-social-media-herausforderung-fuer-die-webarchivierung-1 https://doi.org/10.25798/ak8r-eg12

Bibliographical note

Funding Information:
Melanie Andresen’s work on this paper was funded by the Landesforschungsförderung Hamburg in the context of the project hermA [Ga17] (LFF-FV 35) at Universitčt Hamburg.

Publisher Copyright:
© 2020 Gesellschaft fur Informatik (GI). All rights reserved.

Research areas and keywords

Language Studies
annotation
Academic language
German
machine learning
classification
Academic language
Annotation
Classification
German
Machine learning

Access to Document

10.18420/inf2020_124Licence: CC BY-SA

1 Finished

KoLaS: Kommentiertes Lernendenkorpus Akademisches Schreiben
Knorr, D. (Project manager, academic) & Andresen, M. (Partner)
30.10.11 → 31.12.16
Project: Research

File

1 Journal articles

Zwischen Forscher-, Verfasser- und Erzähler-Ich: Eine korpuslinguistische Studie zur Konstruktion von Selbstreferenz und zu ihrer Einsatzmöglichkeit in der Schreibberatungsausbildung
Knorr, D., 04.2021, In: Zeitschrift für Interkulturellen Fremdsprachenunterricht. 26, 1, p. 137–160 24 p.
Research output: Journal contributions › Journal articles › Research › peer-review

Open Access

Commented Learner Corpus Academic Writing; Kommentiertes Lernendenkorpus akademisches Schreiben
Knorr, D. (Creator) & Andresen, M. (Data Collector), Zentrum für Nachhaltiges Forschungsdatenmanagement Hamburg, 18.11.2017
DOI: 10.25592/uhhfdm.8322, https://www.fdr.uni-hamburg.de/record/8326
Dataset

Cite this

Andresen, M., & Knorr, D. (2020). Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning. In R. H. Reussner, A. Koziolek, & R. Heinrich (Eds.), Informatik 2020 - Back to the future: 50. Jahrestagung der Gesellschaft für Informatik vom 28. September - 2. Oktober 2020, virtual (pp. 1327-1333). (Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI); Vol. P-307). Gesellschaft für Informatik e.V.. https://doi.org/10.18420/inf2020_124

Andresen, Melanie ; Knorr, Dagmar. / Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning. Informatik 2020 - Back to the future: 50. Jahrestagung der Gesellschaft für Informatik vom 28. September - 2. Oktober 2020, virtual. editor / Ralf H. Reussner ; Anne Koziolek ; Robert Heinrich. Bonn : Gesellschaft für Informatik e.V., 2020. pp. 1327-1333 (Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)).

@inbook{aeeb656a92ff4a459da9122c74c22472,

title = "Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning",

abstract = "The use of the pronoun ich ({\textquoteleft}I{\textquoteright}) in academic language is a source of constant debate and a frequent cause of insecurity for students. We explore manually annotated instances of I from a German learner corpus. Using machine learning techniques, we investigate to what extent it is possible to automatically distinguish between different types of I usage (author I vs. narrator I). We additionally inspect which context words are good indicators of one type or the other. The results show that an automatic classification is not straightforward, but the distinctive features are in line with previous research. The results of the automatic classification are not perfect, but would greatly facilitate manual annotation. The distinctive words are in line with previous research and indicate that the author I is a more homogeneous class.",

keywords = "Language Studies, Korpuslinguistik, annotation, Academic language, German, machine learning, classification, Academic language, Annotation, Classification, German, Machine learning",

author = "Melanie Andresen and Dagmar Knorr",

note = "Funding Information: Melanie Andresen{\textquoteright}s work on this paper was funded by the Landesforschungsf{\"o}rderung Hamburg in the context of the project hermA [Ga17] (LFF-FV 35) at Universit{\v c}t Hamburg. Publisher Copyright: {\textcopyright} 2020 Gesellschaft fur Informatik (GI). All rights reserved.; 50th Annual Conference of the German Informatics Society - INFORMATIK 2020 : Back to the Future, INFORMATIK 2020 ; Conference date: 28-09-2020 Through 02-10-2020",

year = "2020",

doi = "10.18420/inf2020\_124",

language = "English",

series = "Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)",

publisher = "Gesellschaft f{\"u}r Informatik e.V.",

pages = "1327--1333",

editor = "Reussner, \{Ralf H.\} and Anne Koziolek and Robert Heinrich",

booktitle = "Informatik 2020 - Back to the future",

address = "Germany",

url = "https://informatik2020.gi.de/, https://gi.de/themen/beitrag/politik-in-den-social-media-herausforderung-fuer-die-webarchivierung-1, https://doi.org/10.25798/ak8r-eg12",

}

Andresen, M & Knorr, D 2020, Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning. in RH Reussner, A Koziolek & R Heinrich (eds), Informatik 2020 - Back to the future: 50. Jahrestagung der Gesellschaft für Informatik vom 28. September - 2. Oktober 2020, virtual. Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI), vol. P-307, Gesellschaft für Informatik e.V., Bonn, pp. 1327-1333, 50th Annual Conference of the German Informatics Society - INFORMATIK 2020, Karlsruhe, Baden-Württemberg, Germany, 28.09.20. https://doi.org/10.18420/inf2020_124

Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning. / Andresen, Melanie; Knorr, Dagmar.
Informatik 2020 - Back to the future: 50. Jahrestagung der Gesellschaft für Informatik vom 28. September - 2. Oktober 2020, virtual. ed. / Ralf H. Reussner; Anne Koziolek; Robert Heinrich. Bonn: Gesellschaft für Informatik e.V., 2020. p. 1327-1333 (Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI); Vol. P-307).

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

TY - CHAP

T1 - Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning

AU - Andresen, Melanie

AU - Knorr, Dagmar

N1 - Conference code: 50

PY - 2020

Y1 - 2020

N2 - The use of the pronoun ich (‘I’) in academic language is a source of constant debate and a frequent cause of insecurity for students. We explore manually annotated instances of I from a German learner corpus. Using machine learning techniques, we investigate to what extent it is possible to automatically distinguish between different types of I usage (author I vs. narrator I). We additionally inspect which context words are good indicators of one type or the other. The results show that an automatic classification is not straightforward, but the distinctive features are in line with previous research. The results of the automatic classification are not perfect, but would greatly facilitate manual annotation. The distinctive words are in line with previous research and indicate that the author I is a more homogeneous class.

AB - The use of the pronoun ich (‘I’) in academic language is a source of constant debate and a frequent cause of insecurity for students. We explore manually annotated instances of I from a German learner corpus. Using machine learning techniques, we investigate to what extent it is possible to automatically distinguish between different types of I usage (author I vs. narrator I). We additionally inspect which context words are good indicators of one type or the other. The results show that an automatic classification is not straightforward, but the distinctive features are in line with previous research. The results of the automatic classification are not perfect, but would greatly facilitate manual annotation. The distinctive words are in line with previous research and indicate that the author I is a more homogeneous class.

KW - Language Studies

KW - Korpuslinguistik

KW - annotation

KW - Academic language

KW - German

KW - machine learning

KW - classification

KW - Academic language

KW - Annotation

KW - Classification

KW - German

KW - Machine learning

UR - https://www.scopus.com/pages/publications/85127357898

UR - https://www.mendeley.com/catalogue/74ed2ea8-4157-36bd-9677-24ac22c76c5e/

U2 - 10.18420/inf2020_124

DO - 10.18420/inf2020_124

M3 - Article in conference proceedings

T3 - Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)

SP - 1327

EP - 1333

BT - Informatik 2020 - Back to the future

A2 - Reussner, Ralf H.

A2 - Koziolek, Anne

A2 - Heinrich, Robert

PB - Gesellschaft für Informatik e.V.

CY - Bonn

T2 - 50th Annual Conference of the German Informatics Society - INFORMATIK 2020

Y2 - 28 September 2020 through 2 October 2020

ER -

Andresen M, Knorr D. Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning. In Reussner RH, Koziolek A, Heinrich R, editors, Informatik 2020 - Back to the future: 50. Jahrestagung der Gesellschaft für Informatik vom 28. September - 2. Oktober 2020, virtual. Bonn: Gesellschaft für Informatik e.V. 2020. p. 1327-1333. (Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI)). doi: 10.18420/inf2020_124

Exploring the Use of the Pronoun I in German Academic Texts with Machine Learning

Abstract

Bibliographical note

Research areas and keywords

Access to Document

Fingerprint

Projects

KoLaS: Kommentiertes Lernendenkorpus Akademisches Schreiben

Research output

Zwischen Forscher-, Verfasser- und Erzähler-Ich: Eine korpuslinguistische Studie zur Konstruktion von Selbstreferenz und zu ihrer Einsatzmöglichkeit in der Schreibberatungsausbildung

Datasets

Commented Learner Corpus Academic Writing; Kommentiertes Lernendenkorpus akademisches Schreiben

Cite this