topicmodelling
news_topicModellingtopic_modelling_datasettopic-modelling-Prozhito
OVERVIEW
Dataset contains csv-tables which include topics (one topic is a list of 10 words) generated from the corpus of texts "Prozhito".
The topics were generated with topic modelling method using library Gensim. All the tables have columns "full_topic" (contain the whole topic consisting of 10 words) and column "words with frep >= 0.03" (contain "the heaviest" words for this topic).
The tables that were processed manually also contain column "topic". It contains one-word theme… See the full description on the dataset page: https://huggingface.co/datasets/PolinaStaroverova/topic-modelling-Prozhito.