Digital Humanities

Chair: Florian Meier


SentText: A Tool for Lexicon-Based Sentiment Analysis in Digital Humanities

Thomas Schmidt, Johanna Dangel, Christian Wolff

Media Informatics Group, University of Regensburg

Abstract

We present SentText, a web-based tool to perform and explore lexicon-based sentiment analysis on texts, specifically developed for the Digital Humanities (DH) community. The tool was developed integrating ideas of the user centered design process and we gathered requirements via semi-structured interviews. The tool offers the functionality to perform sentiment analysis with predefined sentiment lexicons or self-adjusted lexicons. Users can explore results of sentiment analysis via various visualizations like bar or pie charts and word clouds. It is also possible to analyze and compare collections of documents. Furthermore, we have added a close reading function enabling researchers to examine the applicability of sentiment lexicons for specific text sorts. We report upon the first usability tests with positive results. We argue that the tool is beneficial to explore lexicon-based sentiment analysis in the DH but can also be integrated in DH-teaching.

Keywords: Sentiment Analysis, Dictionary-Based Approaches, Digital Humanities, Usability, Tool, User Centered Design, Lexicon-Based Approaches

Short Paper + Demo


Same same, but different? On the Relation of Information Science and the Digital Humanities

A Scientometric Comparison of Academic Journals Using LDA and Hierarchical Clustering

Manuel Burghardt, Jan Luhmann

Computational Humanities Group, Leipzig University, Germany

Abstract

In this paper we investigate the relationship of information science (IS) and the digital humanities (DH) by means of a scientometric comparison of academic journals from the respective disciplines. In order to identify scholarly practices for both disciplines, we apply a recent variant of LDA topic modeling that makes use of additional hierarchical clustering. The results reveal the existence of characteristic topic areas for both IS (information retrieval, information seeking behavior, scientometrics) and DH (computational linguistics, distant reading and digital editions) that can be used to distinguish them as disciplines in their own right. However, there is also a larger shared area of practices related to information management and also a few shared topic clusters that indicate a common ground for – mostly methodological – exchange between the two disciplines.

Keywords: scientometrics; information science; digital humanities; LDA topic modeling; hierarchical clustering

Long Paper


Grundlagenermittlung für die digitale Werkbank qualitativ-hermeneutisch arbeitender Geisteswissenschaftlerinnen

Exploration geisteswissenschaftlicher Forschung mit Fokus auf Exzerpten und Literaturverwaltung

Michael Achmann, Florin Schwappach

Lehrstuhl für Medieninformatik, Universität Regensburg

Abstract

Dieser Beitrag berichtet von einer Fallstudie zum wissenschaftlichen Arbeiten mit Nachwuchswissenschaftlerinnen. Der Fokus der Untersuchung lag auf den Aktivitäten Notieren, Exzerptproduktion und Literaturverwaltung bei qualitativ-hermeneutisch arbeitenden Geisteswissenschaftlerinnen. Das Ergebnis legt nahe, dass vorhandene Literaturverwaltungssoftware nicht zum mentalen Modell der Geisteswissenschaftlerinnen passt, da dieses Notizen und Exzerpte im Mittelpunkt eines Bibliographischen Eintrags sehen. Entsprechend sollten die Digital Humanities bei der Entwicklung zukünftiger Werkzeuge das Notieren und die Literaturverwaltung, sowie der Verknüpfung beider Aktivitäten stärker in den Fokus setzen. Zur Verifizierung der Erkenntnisse aus der Fallstudie sind weitere quantitative Studien notwendig.

Keywords: digital humanities, digital research environment, personal information management, scholarly research, grounded theory, information behaviour

Long Paper

Event Timeslots (1)

Track 1
-