Biases can arise and be introduced during each phase of a supervised learning pipeline, eventually leading to harm. Within the task of automatic abusive language detection, this matter becomes particularly severe since unintended bias towards sensitive topics such as gender, sexual orientation, or ethnicity can harm underrepresented groups. The role of the datasets used to train these models is crucial to address these challenges. In this contribution, we investigate whether explainability methods can expose racial dialect bias attested within a popular dataset for abusive language detection. Through preliminary experiments, we found that pure explainability techniques cannot effectively uncover biases within the dataset under analysis: the rooted stereotypes are often more implicit and complex to retrieve.
Exposing racial dialect bias in abusive language detection: can explainability play a role?
Morini V
2023
Abstract
Biases can arise and be introduced during each phase of a supervised learning pipeline, eventually leading to harm. Within the task of automatic abusive language detection, this matter becomes particularly severe since unintended bias towards sensitive topics such as gender, sexual orientation, or ethnicity can harm underrepresented groups. The role of the datasets used to train these models is crucial to address these challenges. In this contribution, we investigate whether explainability methods can expose racial dialect bias attested within a popular dataset for abusive language detection. Through preliminary experiments, we found that pure explainability techniques cannot effectively uncover biases within the dataset under analysis: the rooted stereotypes are often more implicit and complex to retrieve.File | Dimensione | Formato | |
---|---|---|---|
prod_479349-doc_196638.pdf
accesso aperto
Descrizione: Preprint - Exposing racial dialect bias in abusive language detection: can explainability play a role?
Tipologia:
Versione Editoriale (PDF)
Dimensione
840.75 kB
Formato
Adobe PDF
|
840.75 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.