Exploring and repairing gender fairness violations in word embedding-based sentiment analysis model through adversarial patches

• Main Authors: KHOO, Lin Sze, BAY, Jia Qi, YAP, Ming Lee Kimberly, LIM, Mei Kuan, CHONG, Chun Yong, YANG, Zhou, LO, David
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Fairness testing; Automated program repair; Sentiment analysis; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/8514; https://ink.library.smu.edu.sg/context/sis_research/article/9517/viewcontent/Exploring_and_Repairing_Gender_Fairness_Violations_in_Word_Embedding_based_Sentiment_Analysis_Model_through_Adversarial_Patches.pdf
• Institution: Singapore Management University

With the advancement of sentiment analysis (SA) models and their incorporation into our daily lives, fairness testing on these models is crucial, since unfair decisions can cause discrimination to a large population. Nevertheless, some challenges in fairness testing include the unknown oracle, the d...