This set of dataframes were used in our last paper :

Ollivier K, Boldrini C, Passarella A, Conti M (2022) Structural invariants and semantic fingerprints in the “ego network” of words. PLoS ONE 17(11): e0277182. https://doi.org/10.1371/journal.pone.0277182

root/ ├─ bert_vec/ ├─ egonets/ ├─ topics_distrib/

Four datasets were extracted from Twitter:

Journalists from the NYT Science writers Random users #1 Random users #2

Data files with content derivated from these four datasets are generally prefixed respectively with : nyt, science, random1, random2.

In order to comply with GDPR rules, we fully anonymized the results.

Directory egonets/, contains the egonetwork structures. Even if the words are replaced by ids in order to maintain anonymity, main structural results can be derived from those files.

Directory bert_vec/ contains the BERT embeddings after being reduced by UMAP.

The directory topics_distrib/ contains the dataframes where the topic distribution vectors are stored.