On Domain-specific Topic Modelling Using the Case of a Humanities Journal
Basic data for this talk
Type of talk: scientific Talk
Name der Vortragenden: Braun, Tanya
Date of talk: 26/09/2023
Talk language: English
URL of slides: https://www.fdr.uni-hamburg.de/record/13423
Information about the event
Name of the event: CHAI 2023 3rd Workshop on Humanities-centred AI, co-located with KI 2023
Event period: 26/09/2023
Event location: Berlin
Event website: https://www.csmc.uni-hamburg.de/ki2023-chai
Abstract
Topic modelling techniques have been an important tool for meaningful information retrieval. They also hold the potential to support researchers in areas such as humanities in exploring corpora of different topics in an automated way. One prominent method, latent Dirichlet allocation (LDA), describes documents as distributions over topics and topics as distributions over words. Most applications of LDA focus on sets of tweets, news articles, wikipedia entries, or academic publications covering various topics in a large corpus. In this article, LDA is used in a rather opposite setting: a domain-specific, small-scale corpus in the form of an academic journal concerned with the studies of modern and ancient manuscripts. From this case study, we infer steps specific to dealing with domain-specific corpora.Keywords: topic modelling; LDA; manuscript cultures
Speakers from the University of Münster
| Braun, Tanya |
Publications referred to in the talk
Redzuan, Nadja; Möller, Ralf; Gehrke, Marcel; Braun, Tanya (2023) In: CHAI 2023 3rd Workshop on Humanities-centred AI, co-located with KI 2023, Berlin, Germany. CEUR. Research article in digital collection (conference) | Peer reviewed | Published |