@inProceedings{Kokkinakis-Dimitrios2015-215535, title = {Gender-Based Vocation Identification in Swedish 19th Century Prose Fiction using Linguistic Patterns, NER and CRF Learning}, abstract = {This paper investigates how literature could be used as a means to expand our understanding of history. By applying macroanalytic techniques we are aiming to investigate how women enter literature and particularly which functions they assume, their working patterns and if we can spot differences in how often male and female characters are mentioned with various types of occupational titles (vocation) in Swedish literary texts. Modern historiography, and especially feminist and women’s history has emphasized a relative invisibility of women’s work and women workers. The reasons behind this are manifold, and the extent, the margin of error in terms of women’s work activities is of course hard to assess. Therefore, vocation identification can be used as an indicator for such exploration and we present a hybrid system for automatic annotation of vocational signals in 19th century Swedish prose fiction. Beside vo-cations, the system also assigns gender (male, female or unknown) to the vocation words, a prerequisite for the goals of the study and fu-ture in-depth explorations of the corpora.}, booktitle = {Proceedings of the Fourth Workshop on Computational Linguistics for Literature (Clfl). Co-located with the NAACL/HLT. Denver, Colorado, USA}, author = {Kokkinakis, Dimitrios and Ighe, Ann and Malm, Mats}, year = {2015}, pages = {9}, } @inProceedings{Kokkinakis-Dimitrios2015-225762, title = {Detecting Reuse of Biblical Quotes in Swedish 19th Century Fiction using Sequence Alignment}, abstract = {Text reuse, a form of text repetition, recycling or borrowing, is a theoretically and practically interesting problem that has attracted considerable attention during the last years e.g. in the cultural heritage context (historical and comparative linguistics); in the context of social network propagation of ideas and in the measuring of journalistic reuse. In this paper we briefly outline and experiment with a method used for biological sequence alignment that have been also used in humanities research for e.g. the detection of similar passages in the complete works of Voltaire and 18th century French encyclopedias or for tracing how and which ideas spread in 19th century US-newspaper collections. We use available software (text-PAIR: Pairwise Alignment for Intertextual Relations) and experiment with the Charles XII Bible translation into Swedish, completed in 1703, against the content of the Swedish prose fiction 1800-1900, in order to automatically detect passages taken from this particular Bible translation in the prose fiction corpus.}, booktitle = {Corpus-based Research in the Humanities workshop (CRH), 10 December 2015 Warsaw, Poland }, author = {Kokkinakis, Dimitrios and Malm, Mats}, year = {2015}, ISBN = {978-83-63159-19-1}, pages = {79--86}, }