Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
mathstodon.xyz is one of the many independent Mastodon servers you can use to participate in the fediverse.
A Mastodon instance for maths people. We have LaTeX rendering in the web interface!

Administered by:

Server stats:

3K
active users

mathstodon.xyz: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.6

#culturalanalytics

0 posts0 participants0 posts today
Continued thread
Public
JCLS

Feldkamp et al. reveal diverse perspectives on literary quality and show that expert opinion often conflicts with crowd-sourced ratings & award nominations, highlighting the complexity of measuring literary quality. doi.org/10.48694/jcls.3908 #CLS #CCLS24 #LiteraryQuality #CulturalAnalytics

Journal of Computational Literary StudiesMeasuring Literary Quality. Proxies and PerspectivesComputational studies of literature use proxies like sales numbers, human judgments, or canonicity to estimate literary quality. However, many quantitative use one such measure as a gold standard without fully reflecting on what it represents. We examine the interrelation of 14 proxies of literary quality in novels published in the US from the late 19th to 20th century, distinguishing between expert-based judgments (e.g., syllabi, anthologies) and crowd-based ones (e.g., GoodReads ratings). We show that works favored in expert-based judgments often score lower on GoodReads, while award-nominated works tend to circulate more widely in libraries. Generally, two main kinds of `quality perception' emerge as we map the literary judgment landscape: One associated with canonical literature and one with more popular literature. Additionally, prestige in genre literature, reflected in awards like the Hugo Award, forms a distinct category, more aligned with popular than canonical proxies.
Public
Andres Karjus

Submission open until 15.10 for
#DHNB2025 Conference "Digital Dreams and Practices", this time held in Tartu, Estonia on 5-7 March 2025
#DH #CUDAN #culturalanalytics #digitalhumanities
Invited topics include but are not limited to:
(1) integration of trad humanities w computational techniques
(2) transition of #DH from the academic "ivory tower" to societal practice;
(3) practical applications of #AI
Submission types: long&short papers, abstracts/posters.
More info here: dhnb.eu/conferences/dhnb2025

Public
Harald Klinke

#CulturalAnalytics at its best:

Researchers from Tallinn University have published a groundbreaking study on Tinder's gendered self-representation, employing machine learning to analyze 10,680 profiles. This comprehensive analysis not only identifies key visual self-representation trends but also opens new avenues for cross-platform and cultural research in digital visual culture.
osf.io/preprints/socarxiv/m54z
#MachineLearning #GenderStudies #cudan

A scatter plot showing numerous small images grouped by visual similarity, with larger representative images of different genres highlighted around the edges.
Continued thread
Public
Harald Klinke

AI image synthesis as a reflexive tool in cultural analysis. This study delves into #CriticalImageSynthesis using systems like DALL-E and Stable Diffusion, revealing biases within machine vision representations. By framing AI synthesis as inverted machine vision, it prompts a closer look at cultural portrayals. The project overlays AI-generated images with speculative textual descriptors, creating a visual-lexical poetry fusion.
olh.openlibhums.org/article/id
#AIResearch #CulturalAnalytics

Public
NordicBaltic DH Community

📣 Fantastic news for the #DigitalHumanities #GLAM #ComputationalHumanities #CulturalAnalytics #CulturalHeritage #ResearchDataManagement #OpenHumanities #DigitalCulture communities!
We have released our #CallForSubmissions for the #DHNB2024 conference at the Icelandic Center for Digital Humanities and Arts!
📄 CALL FOR SUBMISSIONS dhnb.eu/conferences/dhnb2024/c
📅 DEADLINE for submissions: 21st Jan 2024
🌋 WHERE? Reykjavík, Iceland 🇮🇸
📅 WHEN? 27th-31st May 2024
ℹ️ INFO on our WEBSITE dhnb.eu/conferences/dhnb2024/

dhnb.euDHNB 2024: Call for Proposals – DHNB
Public *
Maria Antoniak

Presenting Riveter 💪, a Python package to measure social dynamics between personas mentioned in text.

Given a verb lexicon, Riveter 💪 can extract entities and visualize relationships between them.

Package: github.com/maartensap/riveter-

Paper: maartensap.com/pdfs/antoniak20

Video: youtube.com/watch?v=Uftyd8eCmF

Demo Notebook: github.com/maartensap/riveter-

With Anjalie Field, Jimin Mun, Melanie Walsh, Lauren Klein, Maarten Sap

Verb counts for pronoun groups in Pride and Prejudice, using RIVETER’s visualization functions. Labels include both the verb and the position (nsubj or dobj) of the pronoun group, and the pronoun groups were captured via RIVETER’s customizable entity discovery function. Feminine pronouns are more frequently used in low power positions.
Figure from Sap et al. (2017) illustrating power and agency connotation frames extracted on an excerpt from the Sherlock Holmes (2009) film screenplay. Each connotation frame pertains to a verb predicate and its agent and theme.
#ACL2023#DH2023#CulturalAnalytics
Public
M_K_Schumacher

Achtung! – Nur noch wenige Tage bis zur Einreichungsfrist für den 4. Workshop der GI-Fachgruppe "Informatik und Digital Humanities". Thema des Workshops ist “Digital Cultures & Cultural Analytics”. Bis zum 5. Mai 2023 könnt ihr noch ein Paper einreichen (keine Verlängerung möglich). CfP: fg-infdh.gi.de/aktivitaeten/in

(Gesendet mit herzlichen Grüßen von Fachgruppenleiter Manuel Burghardt 👋 )

fg-infdh.gi.deInfDH-Workshop 2023 - FG InfDH
#DigitalHumanities#CulturalAnalytics#DH
Public
Matt L.

If you need to wrangle with EEBO-TCP for your text analysis project, consider using the EarlyPrint project corpus. They've done a bunch of preprocessing to transform "the early English print record, from 1473 to the early 1700s, into a linguistically annotated and deeply searchable text archive." Documentation and tutorials are all really thorough. earlyprint.org/about/ humanitiesdata.com/resources/4 #CulturalAnalytics #dh #opendata #corpora #eebo-tcp

EarlyPrintAboutA collaborative effort—centered doubly at Northwestern University and Washington University in St. Louis—to transform the early English print record, from 1473 to the early 1700s, into a linguistically annotated and deeply searchable text corpus.
SearchLive feeds
About