BibTeX

@incollection{fridlund-etal-2022-trawling-319822,
	title        = {Trawling and Trolling for Terrorists in the Digital Gulf of Bothnia: Cross-lingual Text Mining for the Emergence of Terrorism in Swedish and Finnish Newspapers, 1780–1926},
	abstract     = {In pursuing the historical emergence of the discourse on terrorism, this study trawls the “digital Gulf of Bothnia” in the form of a corpus of combined Swedish and Finnish digitized newspaper texts. Through a cross-lingual exploration of the uses of the concept of terrorism in historical Swedish and Finnish news, we examine meanings anchored in the two culturally close but still decidedly different national political contexts. The study is an outcome of an integrative interdisciplinary effort by Swe-Clarin, using resources accessible through the CLARIN infrastructure to enrich scholarship in the humanities. The capabilities of the corpus tool Korp enable us to affirm prior research on the conceptual history of terrorism, but also to suggest a complex and diverse picture of the connotations of terrorism, both as state and sub-state violence up until the 20th century. At the same time, the study allows us to explore the potentials of cross-lingual text mining for historical analysis of national online newspaper corpora provided by Swe-Clarin and FIN-CLARIN.},
	booktitle    = {CLARIN: The Infrastructure for Language Resources, eds. Darja Fišer & Andreas Witt},
	author       = {Fridlund, Mats and Brodén, Daniel and Jauhiainen, Tommi and Malkki, Leena and Olsson, Leif-Jöran and Borin, Lars},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin, Boston},
	ISBN         = {9783110767346},
	pages        = {781--802},
}

@incollection{saxena-etal-2022-linguistic-317923,
	title        = {A linguistic sketch of Kanashi},
	booktitle    = {Synchronic and Diachronic Aspects of Kanashi},
	editor       = {Anju Saxena and Lars Borin},
	author       = {Saxena, Anju and Borin, Lars and Comrie, Bernard and Sagar, Padam},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
	pages        = {53--127},
}

@incollection{saxena-borin-2022-introduction-317921,
	title        = {Introduction: Kanashi, its speakers, its linguistic and extralinguistic context},
	booktitle    = {Synchronic and diachronic aspects of Kanashi},
	editor       = {Anju Saxena and Lars Borin},
	author       = {Saxena, Anju and Borin, Lars},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
	pages        = {3--11},
}

@incollection{saxena-etal-2022-clues-317928,
	title        = {Clues to Kanashi prehistory 1: Loanword adaptation in nouns and adjectives},
	booktitle    = {Synchronic and Diachronic Aspects of Kanashi},
	editor       = {Anju Saxena and Lars Borin},
	author       = {Saxena, Anju and Borin, Lars and Comrie, Bernard},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
	pages        = {173--213},
}

@incollection{saxena-etal-2022-linguistic-317924,
	title        = {Linguistic variation: A challenge for describing the phonology of Kanashi},
	booktitle    = {Synchronic and Diachronic Aspects of Kanashi},
	editor       = {Anju Saxena and Lars Borin},
	author       = {Saxena, Anju and Sjöberg, Anna and Sagar, Padam and Borin, Lars},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
	pages        = {131--144},
}

@incollection{saxena-etal-2022-kanashi-317930,
	title        = {Kanashi and West Himalayish: Genealogy, language contact, prehistoric migrations},
	booktitle    = {Synchronic and Diachronic Aspects of Kanashi},
	editor       = {Anju Saxena and Lars Borin},
	author       = {Saxena, Anju and Borin, Lars and Comrie, Bernard},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
	pages        = {237--254},
}

@edited_book{saxena-borin-2022-synchronic-317920,
	title        = {Synchronic and diachronic aspects of Kanashi},
	editor       = {Saxena, Anju and Borin, Lars},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
}

@incollection{saxena-etal-2022-clues-317929,
	title        = {Clues to Kanashi prehistory 2: Loanword adaptation in verbs},
	booktitle    = {Synchronic and Diachronic Aspects of Kanashi},
	editor       = {Anju Saxena and Lars Borin},
	author       = {Saxena, Anju and Borin, Lars and Comrie, Bernard},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
	pages        = {215--233},
}

@incollection{saxena-borin-2022-then-317927,
	title        = {And then there was one: Kanashi numerals from borrowed superdiversity to borrowed uniformity},
	booktitle    = {Synchronic and Diachronic Aspects of Kanashi},
	editor       = {Anju Saxena and Lars Borin},
	author       = {Saxena, Anju and Borin, Lars},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {9783110703153},
	pages        = {145--170},
}

@techreport{hammarstedt-etal-2022-sparv-318399,
	title        = {Sparv 5 Developer’s Guide},
	abstract     = {The Sparv Pipeline developed by Språkbanken Text is a text analysis tool run from the command line. 
This Developer’s Guide describes its general structure and key concepts and serves as an API documentation. Most importantly, it  describes how to write plugins for Sparv 5 so that you can add your own functions to the toolkit.},
	author       = {Hammarstedt, Martin and Schumacher, Anne and Borin, Lars and Forsberg, Markus},
	year         = {2022},
}

@incollection{pettersson-borin-2022-swedish-323276,
	title        = {Swedish Diachronic Corpus},
	abstract     = {The recently compiled Swedish Diachronic Corpus offers access to a total of approximately 16 billion words, covering texts from the 13th century onwards. The corpus contains 14 main genres, with a number of subgenres, compiled from a wide range of sources, including corpus providers and libraries as well as individual researchers and private citizens. All texts in the corpus follow a consistent format, are extensively annotated with metadata, and freely available for download. We firmly believe that the existence of a Swedish diachronic corpus among the resources offered by CLARIN will open up avenues to new, interesting research questions within humanities research, and be a valuable resource for large-scale studies of the Swedish language throughout history – studies that have previously been impossible to conduct in a thorough and consistent manner. Thanks to its embedding in the CLARIN context it also carries the potential to enable broad historical studies from a comparative European perspective.},
	booktitle    = {CLARIN: The infrastructure for language resources},
	editor       = {Darja Fišer and Andreas Witt},
	author       = {Pettersson, Eva and Borin, Lars},
	year         = {2022},
	publisher    = {De Gruyter Mouton},
	address      = {Berlin},
	ISBN         = {978-3-11-076734-6},
	pages        = {561–585},
}

@techreport{hammarstedt-etal-2022-sparv-318405,
	title        = {Sparv 5 User Manual},
	abstract     = {The Sparv Pipeline developed by Språkbanken Text is a text analysis tool run from the command line. 
This user manual describes how to get Sparv 5 up and running on your own machine, how to configure it and how to use it for annotating your own corpora.},
	author       = {Hammarstedt, Martin and Schumacher, Anne and Borin, Lars and Forsberg, Markus},
	year         = {2022},
	publisher    = {Institutionen för svenska, flerspråkighet och språkteknologi},
	address      = {Göteborg},
}

@article{borin-2022-that-322872,
	title        = {All that glitters . . .  : 
Interannotator agreement in natural language processing},
	abstract     = {Evaluation has emerged as a central concern in natural language processing (NLP) over the last few decades. Evaluation is done against a gold standard, a manually linguistically annotated dataset, which is assumed to provide the ground truth against which the accuracy of the NLP system can be assessed automatically. In this article, some methodological questions in connection with the creation of gold standard datasets are discussed, in particular (non-)expectations of linguistic expertise in annotators and the interannotator agreement measure standardly but unreflectedly used as a kind of quality index of NLP gold standards.},
	journal      = {Nordlyd},
	author       = {Borin, Lars},
	year         = {2022},
	volume       = {46},
	number       = {1},
	pages        = {19--26},
}

@inProceedings{kokkinakis-etal-2022-necessity-321865,
	title        = {The necessity of digital health communication in social media to boost COVID-19 vaccine acceptance.
},
	booktitle    = {ICA Post Conference: Digital Health Communication: Issues and Perspectives. University of Burgundy Franche-Comté, Dijon, France.},
	author       = {Kokkinakis, Dimitrios and Hammarlin, Mia-Marie and Borin, Lars and Miegel, Fredrik},
	year         = {2022},
}

@misc{tahmasebi-etal-2022-proceedings-316661,
	title        = {Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change, May 26-27, 2022, Dublin, Ireland},
	author       = {Tahmasebi, Nina and Montariol, Syrielle  and Kutuzov, Andrey and Hengchen, Simon and Dubossarsky, Haim and Borin, Lars},
	year         = {2022},
	publisher    = {Association for Computational Linguistics},
	address      = {Stroudsburg, PA},
	ISBN         = {978-1-955917-42-1},
}