Refine
Year of publication
- 2024 (149)
- 2023 (262)
- 2022 (305)
- 2021 (293)
- 2020 (245)
- 2019 (387)
- 2018 (262)
- 2017 (262)
- 2016 (284)
- 2015 (301)
- 2014 (304)
- 2013 (302)
- 2012 (333)
- 2011 (329)
- 2010 (343)
- 2009 (369)
- 2008 (312)
- 2007 (312)
- 2006 (330)
- 2005 (303)
- 2004 (323)
- 2003 (254)
- 2002 (250)
- 2001 (221)
- 2000 (245)
- 1999 (236)
- 1998 (242)
- 1997 (220)
- 1996 (202)
- 1995 (192)
- 1994 (175)
- 1993 (155)
- 1992 (144)
- 1991 (100)
- 1990 (108)
- 1989 (111)
- 1988 (104)
- 1987 (105)
- 1986 (81)
- 1985 (84)
- 1984 (75)
- 1983 (70)
- 1982 (57)
- 1981 (54)
- 1980 (61)
- 1979 (58)
- 1978 (52)
- 1977 (32)
- 1976 (30)
- 1975 (28)
- 1974 (17)
- 1973 (12)
- 1972 (17)
- 1971 (11)
- 1970 (2)
- 1969 (2)
- 1968 (2)
- 1967 (1)
- 1963 (1)
- 1925 (1)
Institute
- Fachbereich Medizintechnik und Technomathematik (2083)
- Fachbereich Elektrotechnik und Informationstechnik (1186)
- Fachbereich Wirtschaftswissenschaften (1164)
- Fachbereich Energietechnik (1116)
- Fachbereich Chemie und Biotechnologie (918)
- Fachbereich Maschinenbau und Mechatronik (880)
- Fachbereich Luft- und Raumfahrttechnik (799)
- Fachbereich Bauingenieurwesen (711)
- IfB - Institut für Bioengineering (692)
- INB - Institut für Nano- und Biotechnologien (616)
Language
- German (5145)
- English (4942)
- Russian (14)
- Portuguese (6)
- Italian (5)
- Multiple languages (5)
- Spanish (3)
- Dutch (2)
Document Type
- Article (5628)
- Conference Proceeding (1677)
- Book (1085)
- Part of a Book (576)
- Bachelor Thesis (331)
- Patent (177)
- Report (102)
- Conference: Meeting Abstract (82)
- Doctoral Thesis (82)
- Administrative publication (77)
Keywords
- Amtliche Mitteilung (72)
- Bachelor (34)
- Aachen University of Applied Sciences (31)
- Master (31)
- Prüfungsordnung (31)
- Bauingenieurwesen (30)
- Lesbare Fassung (28)
- Biosensor (25)
- Fachhochschule Aachen (23)
- Illustration (23)
Zugriffsart
- campus (2151)
- weltweit (1896)
- bezahl (788)
- fachbereichsweit (FB4) (38)
Preprint: Detecting sexism in German online newspaper comments with open-source text embeddings
(2024)
Sexism in online media comments is a pervasive challenge that often manifests subtly, complicating moderation efforts as interpretations of what constitutes sexism can vary among individuals. We study monolingual and multilingual open-source text embeddings to reliably detect sexism and misogyny in Germanlanguage online comments from an Austrian newspaper. We observed classifiers trained on text embeddings to mimic closely the individual judgements of human annotators. Our method showed robust performance in the GermEval 2024 GerMS-Detect Subtask 1 challenge, achieving an average macro F1 score of 0.597 (4th place, as reported on Codabench). It also accurately predicted the distribution of human annotations in GerMS-Detect Subtask 2, with an average Jensen-Shannon distance of 0.301 (2nd place). The computational efficiency of our approach suggests potential for scalable applications across various languages and linguistic contexts.