University of Crete emblem University of Crete
Artificial Intelligence
for the Humanities &
Social Sciences

Home Research RT3

RT3 · Research theme

Corpus analysis

NLP and machine learning open new ways to study Modern Greek literature, from individual words to patterns across works.

Explore the research ↓Publications ↗
Handwritten autobiography of Alexandros Papadiamantis, before 1911; contextual manuscript

What can we discover by reading at scale?

Plot word frequencies

A small corpus laboratory

Edit the sample and calculate a word-frequency plot. Results are computed from your text in this browser; the sample is an invented teaching passage, not a TALOS corpus.

View values and method

Unicode words are lowercased; accents are retained. No lemmatization or stop-word removal is applied. The chart shows the ten most frequent forms. A frequency is not a measure of literary importance.

Research scope
  • Build digital corpora of Modern Greek literature.
  • Investigate themes, sentiment, lexical density and syntactic complexity.
  • Study patterns across works and authors, and trace intellectual networks.
Doctoral research

Nineteenth-century Ionian prose fiction

Fotini Koidaki

Identifying novels and building a digital corpus to study cultural features, language and narrative continuities across Ionian prose fiction.

Full project description →
Try Fotini’s text-recognition model →
Research output: 19th century Greek 8.0

Fotini Koidaki’s text-recognition model, 19th century Greek 8.0, uses PyLaia and is available to try in Transkribus.

View and try the model →
Browse the public model catalogue →
People behind the research

Maria Papadopoulou

Leader

Christophe Roche

Co-supervisor

Melina Tamiolaki

Co-supervisor

Rafail Giannadakis

Research Assistant

Tonia Lourentzaki

Research Assistant

Stergios Chatzikyriakidis

Supervisor

Anastasia Natsina

Co-supervisor

Fotini Koidaki

PhD Candidate

Dimitris Bilianos

Post-Doc Researcher