If you are having trouble with the sign in process, please <ContactLink>contact the SSH Open Marketplace team</ContactLink>.

If you are having trouble with the sign up process, please <ContactLink>contact the SSH Open Marketplace team</ContactLink>.

Subject

Social Sciences & Humanities Open Marketplace

Successfully submitted!

Automatically create a TEI-format annotated corpus, using a plaintext file containing the analysed drama. Initially, several preprocessing indicators need to be inserted into the input file including: indication of the name of the author, name of the play, indication of the cast members section, idication of a beginning-end of respective parts of a play.

Using the annotated TEI file, each character's speech is extracted into an individual file.

Using the TF-IDF vectorization, the spoken text of each individual character is converted into a continuous space vector representation.

The continuous vector representations are analyzed using unsupervised clustering algorithm (hierarchical or aglomerative clustering).

Michael Dahnke

Dušan Variš

Analyze the relationships between the characters in a drama based on monologue/dialogue. Create a continuous character representations using their respective speech and group the characters using unsupervised clustering.

Intertextuality phenomena in European drama history

Workflow steps(4)

1 (Optional) Convert plaintext to TEI

2 Extract the speech of the respective characters

3 Create continuous representations of the characters

4 Apply the unsupervised clustering