Skip to content

Latest commit

 

History

History
18 lines (15 loc) · 938 Bytes

README.md

File metadata and controls

18 lines (15 loc) · 938 Bytes

CountryWideTopics

Comprehensive news coverage and article embedding and recommendation, keyword extraction system for NAVER news using doc2vec and tf-idf.

Components

figure1

Contributors

@dnjstlr555 @seny1004 @hyebing @sara4423

Conference

Oh Won Sik, et al. (2022-06-23-25). News Article Recommendation and Curation System based on Document Embedding and Keyword Extraction. Korean Institute of Smart Media 2022 Conference.

Command

save save current crawled data
day (num1) (num2) (num3) -> from today-num1, crawl num3 data per day upto today-num2
category update category variable
word update wordcloud images
doc fit doc2vec model
key extract keywords from articles