No description available.

No description available.

Rap music is one of the biggest music genres in the world today. Since the early days of rap music, references not only to pop culture but also to other rap artists have been an integral part of the lyrics’ artistry. Rappers may use them to introduce their shared personal backgrounds such as where they grew up. In addition, rap musicians reference each other by adopting fragments of lyrics, for example, to give credit. This kind of text reuse can be used to create connections between individual artists. Due to the large amount of lyrics, only automated detection methods can efficiently detect text reuse. In addition, automated methods can also be used to identify similar artists based on their lyrical content. Here, we present a visualization system for analyzing text reuse in rap music lyrics. The system supports the user of detecting text reuse and allusions between songs and exploring connections between artists. For this purpose, we crawled song lyrics and their metadata of selected American rap artists from Genius.com. We also trained a network tailored specifically for rap lyrics, which we named “rapBERTa”, to compute similarities in lyrics.

No description available.

No description available.

This thesis approaches eighteenth-century utopian thinking from a new methodological angle, namely by utilising the Reception Reader, an open-access text reuse detection tool, to study a sub-corpus of 39 utopian works available in ECCO (Eighteenth Century Collections Online), the largest collection of digitised eighteenth-century texts printed in the British and Irish Isles. As the first study of text reuse in utopian thinking, this thesis shows that text reuse detection is a viable method for gaining new insights into eighteenth-century utopian thinking. Engaging with existing theories of text reuse in historical materials, this thesis proposes a theoretical framework that is particularly suited for the study of text reuse in eighteenth-century books, with an emphasis on the interrelationship between text reuse and contemporary print culture. This thesis argues that an investigation of text reuse patterns at three interconnected levels—reflecting print culture, genre popularity, and individual authors’ persuasive strategies—results in a better understanding of the presence and purpose of text reuse in eighteenth-century utopian works. This thesis posits that text reuse was often a deliberate choice on the part of the author to signal belonging to a shared intellectual tradition, and, most importantly, to support the overall critical aim of the utopian work. Individual instances of text reuse in utopian works are signs of deliberate or unintentional engagement with the culture that surrounded these works. A more nuanced interpretation of how utopian thinking interacted with contemporary print culture is crucial for recognising why utopian thinking continued to be prevalent throughout the eighteenth century.

Detecting references and similarities in music lyrics can be a difficult task. Crowdsourced knowledge platforms such as Genius. can help in this process through user-annotated information about the artist and the song but fail to include visualizations to help users find similarities and structures on a higher and more abstract level. We propose a prototype to compute similarities between rap artists based on word embedding of their lyrics crawled from Genius. Furthermore, the artists and their lyrics can be analyzed using an explorative visualization system applying multiple visualization methods to support domain-specific tasks.

No description available.

In this article, we describe a two-step processing pipeline for identifying text reuse of Shakespeare’s Hamlet in a corpus of postmodern fiction by comparing n-grams from both sources. A key feature of our approach lies in a pre-filtering step, in which we select target sentences in the fiction corpus that are potential candidates for Hamlet text reuse. Without pre-filtering, the amount of text reuse pairs (that are no actual quotes) would be extremely high. In a second filtering step, we compare potential text reuse pairs by their vector representation using a neural network trained in an unsupervised manner. We found that using the vector similarity produces a problematic amount of false positives. The created vector representations are created using an unsupervised training approach, resulting in similarity aspects that are unfavorable for our use case.

No description available.