Envargs - Labelling Environmental Belgian Case Law

This dataset contains cases from the Belgian administrative law, the topic of law they belong to, as well as an additional binary label that determines if the case can be considered as an 'environmental law' case. 

Files description: 
- topics_env.csv : the columns contains the list of specific topics that are considered to be 'environmental law' topics. Under each topic is the list of case_numbers that are related to that topic of law. 

- topics_non_env.csv : the columns contains the list of specific topics that are considered not to be 'environmental law' topics. Under each topic is the list of case_numbers that are related to that topic of law. 

- labelled_case_dataset.csv : this file contains all the cases together with their text and their label (0 if non-environmental, 1 if environmental). The columns are the following: ['case_number', 'topic', 'year', 'case_text', 'label']. The 'case_text' filed contain the raw text of the case (no pre-processing applied). 

- labelled_case_dataset_lemmatized.csv: this file contains all the cases together with their text and their label (0 if non-environmental, 1 if environmental). The columns are the following: ['case_number', 'topic', 'year', 'case_text', 'label']. The 'case_text' filed contain the lemmatised version of the cases, stopwords and punctuation signs have been removed too. 

- labelled_case_dataset_no_stopwords.csv : this file contains all the cases together with their text and their label (0 if non-environmental, 1 if environmental). The columns are the following: ['case_number', 'topic', 'year', 'case_text', 'label']. The 'case_text' filed contain the text of the cases, after having removed stopwords and punctuation signs.