Proposed compartmentalized architecture for Context-Sensitive Stance Classification.

مواد مشابهة

• Performance of in-country Stance Classifiers at different context levels.
  حسب: Ramon Villa-Cox (8311131)
  منشور في: (2025)
• Example of the most prominent stance-tags used for each country. Pro-government hashtags tend to support the country’s president (Evo, Piñera, Lenin), the police (ESMAD or Carabineros) or attack the opposition leader (Petro, Correa, CONAIE). Against-government hashtags label the country’s president as a dictator, assassin or traitor, or support the protest (“paro”).
  حسب: Ramon Villa-Cox (8311131)
  منشور في: (2025)
• Out of sample Predictions for the Chilean Referendum at different context levels. These correspond to the classifier trained on the 2019 Chilean Protest Data, but with inverted labels (“Pro” government are considered “Against” the referendum and vice-versa). Model performance metrics correspond to the median of 1000 bootstrapped samples of the Referendum collection, disaggregated by whether a user was seen during training of the Chilean Protest classifier. For each metric, the classifiers whose performance is not statistically different, at a 99% confidence level, from the best-performing model are highlighted in bold. We also highlight in bold the name of the best-performing model if it obtains the best results (or is statistically tied) in all presented metrics. The corresponding confidence bands, computed from the bootstrapped empirical distribution of each metric, are included in
  حسب: Ramon Villa-Cox (8311131)
  منشور في: (2025)
• Macro F-1 (%) score and Area Under de ROC curve for out-of-sample cross-country predictions for classifiers at different context levels. Model performance metrics correspond to the median of 1000 bootstrapped samples from column-country. This excluded users seen during training of the country classifier (row). For each metric, the classifiers whose performance is not statistically different, at a 99% confidence level, from the best-performing model are highlighted in bold. We also highlight in bold the name of the best-performing model if it obtains the best results (or is statistically tied) in all presented metrics. For the Bolivian case study, the worst-performing classifier is highlighted. The corresponding confidence bands, computed from the bootstrapped empirical distribution of each metric, are included in Table 2 of
  حسب: Ramon Villa-Cox (8311131)
  منشور في: (2025)
• Percentage of users, and their respective tweets, in the protest data of country (column) that were also present in the training set of a country (row).
  حسب: Ramon Villa-Cox (8311131)
  منشور في: (2025)