ogencoglu / fair_cyberbullying_detection

Source code and models for the paper "Cyberbullying Detection with Fairness Constraints". IEEE Internet Computing, 2020

Implementation of Cyberbullying Detection with Fairness Constraints - Gencoglu O. (2020) ==================== This repository provides the full implementation with released models. Requires python 3.7 and TensorFlow 2.0 (see requirements.txt).

Main Idea

Can we mitigate the unintended bias of cyberbullying detection models by guiding the model training with fairness constraints?

Quick overview

# list group-specific FNRs/FPRs
fnrs = []
fprs = []
constraints = []
for iden in range(cf.num_identity_groups):
    context_group_subset = context_group.subset(lambda kk=iden: group_tensor[:, kk] > 0)
    fnrs.append(tfco.false_negative_rate(context_group_subset))
    fprs.append(tfco.false_positive_rate(context_group_subset))

# define lower and upper bound constraints (see equation 3 in paper)
constraints.append(tfco.upper_bound(fnrs) - tfco.false_negative_rate(context) <= allowed_fnr_deviation)
constraints.append(tfco.upper_bound(fprs) - tfco.false_positive_rate(context) <= allowed_fpr_deviation)
constraints.append(tfco.false_negative_rate(context) - tfco.lower_bound(fnrs) <= allowed_fnr_deviation)
constraints.append(tfco.false_positive_rate(context) - tfco.lower_bound(fprs) <= allowed_fpr_deviation)

# define problem, optimizer and variables to optimize
problem = tfco.RateMinimizationProblem(objective, constraints)
optimizer = tfco.ProxyLagrangianOptimizerV2(
    optimizer=tf.keras.optimizers.Adam(learning_rate),
    constraint_optimizer=tf.keras.optimizers.Adam(learning_rate),
    num_constraints=problem.num_constraints)
var_list = (constrained_model.trainable_weights + problem.trainable_variables + optimizer.trainable_variables())

Example Results

Quick Reproduction of Results ==================== 1 - Get the data --------------See directory_info in the data directory for the expected directory structure.

-Jigsaw Link -Twitter Link -Wiki Link -Gab Link

2 - Download unconstrained and constrained models --------------Download released models to models directory. See directory_info in the model directory for the expected directory structure.

3 - Run compare_models.ipynb

See source directory.

Training From Scratch ==================== Run the corresponding notebook (e.g. gab_experiment.ipynb) for each experiment in the source directory for reproducing the full results from scratch. Note that the algorithms are non-determinisitic due to random weight initialization of the models.

Relevant configurations are defined in configs.py, e.g.:

--batch_size 128 --epochs 75 --gab_allowed_fnr_deviation 0.10 --gab_allowed_fpr_deviation 0.15 --random_state 42

source directory tree:

├── compare_models.ipynb
├── configs.py
├── embeddings.py
├── evaluation.py
├── gab_experiment.ipynb
├── jigsaw_experiment.ipynb
├── metrics.py
├── model.py
├── plot.py
├── train.py
├── twitter_experiment.ipynb
├── utils.py
└── wiki_experiment.ipynb

Cite ====================

@article{gencoglu2021cyberbullying,
  title={Cyberbullying Detection with Fairness Constraints},
  author={Gencoglu, Oguzhan},
  journal={IEEE Internet Computing},
  doi={10.1109/MIC.2020.3032461},
  pages={20--29},
  volume={25},
  number={1},
  publisher={IEEE Computer Society},
  year={2021}
}

Or

Gencoglu, Oguzhan. "Cyberbullying Detection with Fairness Constraints." IEEE Internet Computing (2020) vol. 25, no. 1, pp. 20-29. doi:10.1109/MIC.2020.3032461