Extraction of Character Profiles from the Gutenberg Archive

Egloff, Mattia; Picca, Davide; Adamou, Alessandro

doi:10.1007/978-3-030-36599-8_32

Cited by 4 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the metadata contain two sets of manually annotated topical labels for each text: "subject" labels and "bookshelf" labels. The subject labels were obtained from the Library of Congress Classification (LCC) or Subject Headings (LCSH) thesauri [50], while the bookshelf labels were created by PG volunteers [43].…”

Section: Discussionmentioning

confidence: 99%

Quantifying the Dissimilarity of Texts

Shade

Altmann

2023

Information

View full text Add to dashboard Cite

Quantifying the dissimilarity of two texts is an important aspect of a number of natural language processing tasks, including semantic information retrieval, topic classification, and document clustering. In this paper, we compared the properties and performance of different dissimilarity measures D using three different representations of texts—vocabularies, word frequency distributions, and vector embeddings—and three simple tasks—clustering texts by author, subject, and time period. Using the Project Gutenberg database, we found that the generalised Jensen–Shannon divergence applied to word frequencies performed strongly across all tasks, that D’s based on vector embedding representations led to stronger performance for smaller texts, and that the optimal choice of approach was ultimately task-dependent. We also investigated, both analytically and numerically, the behaviour of the different D’s when the two texts varied in length by a factor h. We demonstrated that the (natural) estimator of the Jaccard distance between vocabularies was inconsistent and computed explicitly the h-dependency of the bias of the estimator of the generalised Jensen–Shannon divergence applied to word frequencies. We also found numerically that the Jensen–Shannon divergence and embedding-based approaches were robust to changes in h, while the Jaccard distance was not.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantifying the Dissimilarity of Texts

Shade

Altmann

2023

Information

View full text Add to dashboard Cite

show abstract

“…Personality and inner traits, when they are archetypal and stereotypical through arts and literature, can also characterize intangible cultural items. Early eforts in capturing this dimension include employing ontologies to extract personality traits as expressed by authors through texts [51,52].…”

Section: Beyond Movement: Linking Data For Knowledgementioning

confidence: 99%

Digitizing Intangible Cultural Heritage Embodied: State of the Art

Hou

Kenderdine

Picca

et al. 2022

J. Comput. Cult. Herit.

Self Cite

View full text Add to dashboard Cite

Intangible cultural heritage (ICH) as a field of research and site for digital efforts has grown significantly since the UNESCO 2003 Convention for the Safeguarding of Intangible Heritage. In contrast to tangible heritage, where cultural identities are manifested through physical objects, intangible cultural expressions are defined through tacit reliances and embodied practices. Such practices are usually bodily communicated, enacted, socially transmitted, and constantly evolving. Burgeoning trends in computational heritage and ICT applications have played a crucial role in safeguarding ICH as they produce versatile resources while making them accessible to the public. Nevertheless, most of the inventions are object-centric and cater to conserving material-based knowledge bases. Few endeavors thus far have fully supported the recording, representing, and reviving of the living nature of ICH. One of the challenges now faced is to find appropriate forms, together with efficient methods, to document the ephemeral aspects of intangible heritage. Another barrier is to find effective ways to communicate the knowledge inextricably linked to people. In response, recent efforts have embarked on capturing the “live” and “active” facets of the embodied cultures, which entails addressing technological and curatorial complexity to communicate the material and immaterial aspects within a meaningful context. Meanwhile, advancements in experimental museology have opened up new modes of experiential narratives, particularly through visualization, augmentation, participation, and immersive embodiment. Novel practices of cultural data computation and data sculpting have also emerged toward the ideal of knowledge reconstruction. This article outlines state-of-the-art models, projects, and technical practices that have advanced the digitization lifecycle for ICH resources. The review focuses on several critical but less studied tasks within digital archiving, computational encoding, conceptual representation, and interactive engagement with the intangible cultural elements. We aim to identify the advancements and gaps in the existing conventions, and to envision opportunities for transmitting embodied knowledge in intangible heritage.

show abstract

A systematic review of Wikidata in Digital Humanities projects

Zhao

2022

Digital Scholarship in the Humanities

View full text Add to dashboard Cite

Wikidata has been widely used in Digital Humanities (DH) projects. However, a focused discussion regarding the current status, potential, and challenges of its application in the field is still lacking. A systematic review was conducted to identify and evaluate how DH projects perceive and utilize Wikidata, as well as its potential and challenges as demonstrated through use. This research concludes that: (1) Wikidata is understood in the DH projects as a content provider, a platform, and a technology stack; (2) it is commonly implemented for annotation and enrichment, metadata curation, knowledge modelling, and Named Entity Recognition (NER); (3) Most projects tend to consume data from Wikidata, whereas there is more potential to utilize it as a platform and a technology stack to publish data on Wikidata or to create an ecosystem of data exchange; and (4) Projects face two types of challenges: technical issues in the implementations and concerns with Wikidata’s data quality. In the discussion, this article contributes to addressing three issues related to coping with the challenges in the specific context of the DH field based on the research findings: the relevance and authority of other available domain sources; domain communities and their practices; and workflow design that coordinates technical and labour resources from projects and Wikidata.

show abstract

Extraction of Character Profiles from the Gutenberg Archive

Cited by 4 publications

References 5 publications

Quantifying the Dissimilarity of Texts

Quantifying the Dissimilarity of Texts

Digitizing Intangible Cultural Heritage Embodied: State of the Art

A systematic review of Wikidata in Digital Humanities projects

Contact Info

Product

Resources

About