Pinned Repositories
NER_novels
Perform Named Entity Recognition (NER) on french novels from the roman18 corpus with the help of SpaCy.
roman18
Collection de romans français du dix-huitième siècle (1751-1800) / Collection of Eighteenth-Century French Novels (1751-1800)
sentiment_novels
Sentiment analysis on the roman18 corpus
topicmodeling
Doing topic modeling on French 18th century novels in the context of MiMoText project
bibliographie_du_genre_romanesque
Characters_roman18
Exploration of characters data
course-computational-literary-analysis
Course materials for Introduction to Computational Literary Analysis, taught at UC Berkeley in Summer 2018, 2019, and 2020.
Data_to_viz
dataextend
A bot for adding data to wikidata items based on the existing identifiers, external links and wiki links
Doyle
This is an exploration of TF-IDF with a small corpus of novels in four genres: detective, horror, adventure and historical. All novels are written by Arthur Conan Doyle. Distinctive words are visualized with scattertext.
roettger's Repositories
roettger/Doyle
This is an exploration of TF-IDF with a small corpus of novels in four genres: detective, horror, adventure and historical. All novels are written by Arthur Conan Doyle. Distinctive words are visualized with scattertext.
roettger/bibliographie_du_genre_romanesque
roettger/Characters_roman18
Exploration of characters data
roettger/course-computational-literary-analysis
Course materials for Introduction to Computational Literary Analysis, taught at UC Berkeley in Summer 2018, 2019, and 2020.
roettger/Data_to_viz
roettger/dataextend
A bot for adding data to wikidata items based on the existing identifiers, external links and wiki links
roettger/exploring_document_similarities
An exploration of a subcorpus of MiMoText novel corpus (roman18): average sentence length, term frequency distribution, document similarity matrix.
roettger/exploring_spacy
An exploration of SpaCy: POS tagging, computing similarity of words, visualizing POS tags via displacy, finding named entities etc.
roettger/exploring_wordembeddings
Exploring Wordembeddings in "Candide" and in the "Dictionnaire Européens des Lumières"
roettger/git-ws
Dummy repo
roettger/github-slideshow
A robot powered training repository :robot:
roettger/github.io.-
roettger/Iramuteq
roettger/Keyness_Measures
Exploring keyness measures and their features
roettger/KeynessToolsTalk
roettger/paper_preprocessing
roettger/pycon-nlp-in-10-lines
Repository for PyCon 2016 workshop Natural Language Processing in 10 Lines of Code
roettger/pydistinto
pydistinto - a Python implementation of different measures of distinctiveness for contrastive text analysis
roettger/spacy-notebooks
💫 Jupyter notebooks for spaCy examples and tutorials
roettger/SPARQL_with_Python
We can access the MiMoTextBase SPARQL endpoint also with Python, which enables us to directly load and analyze the data we have queried.
roettger/textexplorationen-in-der-digitalen-literaturwissenschaft
roettger/Thesis
roettger/txtlab450
Copy of the txtLAB450 text collection
roettger/wiki-literature
Notebook to compare wiki articles based on weltliteratur/fontane.