GTUT-HT20

1. formatdata.py • This processes the raw data and generates some data files required for the project

2. resolve_data_conflicts.py • This is used for resolving some data conflicts, and also for generating the bigraph file (used in the next step for biclique detection)

3. Generate bicliques using the existing bi-clique detection algorithm as mentioned in the paper

4. format_bicliques.py • Using this code, the bicliques detected in the previous step can be further customized/formatted for more granular analysis

5. scoring_bicliques.py

6. build_similarity_matrix.py

7. build_final_similarity_matrix.py

8. article_n2v_representations.py

9. label_articles.py