Data Exploration

Different tools are provided to help you browse your data:

  • First Corpus Explorer provides a table-like visualization of your dataset,
  • Demography script is useful for getting an overall idea of the dynamics of entities in each field,
  • Distant Reading provides a complete interface for evaluating the temporal trend of textual entities.
  • With Word2Vec Explorer, one can browse the structure of large vocabulary trained from a corpus

Data exploration documentation

Corpus Explorer

Corpus explorer provides a table-like view of your dataset directly online allowing to directly read the content of your corpus. Different filtering option are also provided either globally using the top search box or for each field using the individual search boxes at the bottom. A column may also be hidden using the Toggle option at the ...

Demography

Demography processes each field of the corpus and counts the raw evolution of occurrences of the top items. You will simply be asked to specify the number of top items you wish to evaluate. If you previously customized periods, you can also optionally  choose them   instead of the original time stamps. The script creates ...

Distant Reading

Inspired from Franco Moretti work on literary corpus, this script provides a complete interface (files suffixed by distant.html in the resulting dataset directory) for comparing the dynamics of a series of items in a corpus. It is mainly designed to compare words from a given textual field but could be used for other purposes… Distance reading parameters Textual ...

W2V Explorer

W2V Explorer learns the word embedding of every word (above a given frequency threshold) using the Word2Vec (Mikolov et al. 2013) model in a corpus and visualizing the position of words in a reduced 2 dimensional space generated by t-SNE (Maaten, 2008). Words are also clustered according to their proximity using HDBScan algorithm (Campello et al. 2013). Set ...

Contrast Analysis

Contrast Analysis script proposes to show how much two sub-corpus (defined by the user within a dataset) feature a different set of words in its textual content or entities  in any categorical field.  It uses the excellent library scattertext (Kessler J.S., 2017). See below an interactive example showing which words were  used relatively more often ...

Latest questions in the Q&A forum on data exploration

Filter:AllOpenResolvedClosedUnanswered
AnsweredChiara asked 2 weeks ago • 
34 views1 answers0 votes
AnsweredDéborah Abhervé asked 3 months ago • 
70 views2 answers0 votes
AnsweredKate Li asked 4 months ago • 
123 views3 answers1 votes
AnsweredSLavau asked 8 months ago • 
129 views3 answers0 votes
Resolvedmatias.milia asked 2 years ago • 
478 views0 answers0 votes
Openkatharina_kaeppel asked 3 years ago • 
497 views1 answers0 votes
Resolvedlhoste asked 7 years ago • 
1484 views0 answers0 votes
ResolvedRome asked 1 year ago • 
288 views0 answers0 votes
OpenAgnes Girard asked 3 years ago • 
571 views1 answers0 votes