Recommender engines play a role in the emergence and reinforcement of filter bubbles. When these systems learn that a user prefers content from a particular site, the user will be less likely to be exposed to different sources or opinions and, ultimately, is more likely to develop extremist tendencies. We trace roots of this phenomenon to the way the recommender engine represents news articles. The vectorial features modern systems extract from the plain text of news articles are already highly predictive of the associated news outlet. We propose a new training scheme based on adversarial machine learning to tackle this issue . Our preliminary experiments show that the features we can extract this way are significantly less predictive of the news outlet and thus offer the possibility to reduce the risk of manifestation of new filter bubbles.
{"title":"Fighting Filterbubbles with Adversarial Training","authors":"Lukas Pfahler, K. Morik","doi":"10.1145/3422841.3423535","DOIUrl":"https://doi.org/10.1145/3422841.3423535","url":null,"abstract":"Recommender engines play a role in the emergence and reinforcement of filter bubbles. When these systems learn that a user prefers content from a particular site, the user will be less likely to be exposed to different sources or opinions and, ultimately, is more likely to develop extremist tendencies. We trace roots of this phenomenon to the way the recommender engine represents news articles. The vectorial features modern systems extract from the plain text of news articles are already highly predictive of the associated news outlet. We propose a new training scheme based on adversarial machine learning to tackle this issue . Our preliminary experiments show that the features we can extract this way are significantly less predictive of the news outlet and thus offer the possibility to reduce the risk of manifestation of new filter bubbles.","PeriodicalId":428850,"journal":{"name":"Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127111308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sentiment detection is an important building block for multiple information retrieval tasks such as product recommendation, cyberbullying, fake news and misinformation detection. Unsurprisingly, multiple commercial APIs, each with different levels of accuracy and fairness, are now publicly available for sentiment detection. Users can easily incorporate these APIs in their applications. While combining inputs from multiple modalities or black-box models for increasing accuracy is commonly studied in multimedia computing literature, there has been little work on combining different modalities for increasingfairness of the resulting decision. In this work, we audit multiple commercial sentiment detection APIs for the gender bias in two-actor news headlines settings and report on the level of bias observed. Next, we propose a "Flexible Fair Regression" approach, which ensures satisfactory accuracy and fairness by jointly learning from multiple black-box models. The results pave way for fair yet accurate sentiment detectors for multiple applications.
{"title":"Balancing Fairness and Accuracy in Sentiment Detection using Multiple Black Box Models","authors":"Abdulaziz A. Almuzaini, V. Singh","doi":"10.1145/3422841.3423536","DOIUrl":"https://doi.org/10.1145/3422841.3423536","url":null,"abstract":"Sentiment detection is an important building block for multiple information retrieval tasks such as product recommendation, cyberbullying, fake news and misinformation detection. Unsurprisingly, multiple commercial APIs, each with different levels of accuracy and fairness, are now publicly available for sentiment detection. Users can easily incorporate these APIs in their applications. While combining inputs from multiple modalities or black-box models for increasing accuracy is commonly studied in multimedia computing literature, there has been little work on combining different modalities for increasingfairness of the resulting decision. In this work, we audit multiple commercial sentiment detection APIs for the gender bias in two-actor news headlines settings and report on the level of bias observed. Next, we propose a \"Flexible Fair Regression\" approach, which ensures satisfactory accuracy and fairness by jointly learning from multiple black-box models. The results pave way for fair yet accurate sentiment detectors for multiple applications.","PeriodicalId":428850,"journal":{"name":"Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126993019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Social media has shaken the foundations of our society, unlikely as it may seem. Many of the popular tools used to moderate harmful digital content, however, have received widespread criticism from both the academic community and the public sphere for middling performance and lack of accountability. Though social media research is thought to center primarily on natural language processing, we demonstrate the need for the community to understand multimedia processing and its unique ethical considerations. Specifically, we identify statistical differences in the performance of Amazon Turk (MTurk) annotators when different modalities of information are provided and discuss the patterns of harm that arise from crowd-sourced human demographic prediction. Finally, we discuss the consequences of those biases through auditing the performance of a toxicity detector called Perspective API on the language of Twitter users across a variety of demographic categories.
社交媒体已经动摇了我们社会的基础，尽管看起来不太可能。然而，许多用于缓和有害数字内容的流行工具因表现一般和缺乏问责制而受到学术界和公共领域的广泛批评。虽然社会媒体研究被认为主要集中在自然语言处理上，但我们证明了社区理解多媒体处理及其独特的伦理考虑的必要性。具体来说，我们确定了在提供不同形式的信息时，Amazon Turk (MTurk)注释器性能的统计差异，并讨论了由众包的人类人口统计预测产生的危害模式。最后，我们通过审计一个名为Perspective API的毒性检测器对各种人口统计类别的Twitter用户的语言的性能来讨论这些偏差的后果。
{"title":"Not Judging a User by Their Cover: Understanding Harm in Multi-Modal Processing within Social Media Research","authors":"Jiachen Jiang, Soroush Vosoughi","doi":"10.1145/3422841.3423534","DOIUrl":"https://doi.org/10.1145/3422841.3423534","url":null,"abstract":"Social media has shaken the foundations of our society, unlikely as it may seem. Many of the popular tools used to moderate harmful digital content, however, have received widespread criticism from both the academic community and the public sphere for middling performance and lack of accountability. Though social media research is thought to center primarily on natural language processing, we demonstrate the need for the community to understand multimedia processing and its unique ethical considerations. Specifically, we identify statistical differences in the performance of Amazon Turk (MTurk) annotators when different modalities of information are provided and discuss the patterns of harm that arise from crowd-sourced human demographic prediction. Finally, we discuss the consequences of those biases through auditing the performance of a toxicity detector called Perspective API on the language of Twitter users across a variety of demographic categories.","PeriodicalId":428850,"journal":{"name":"Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124785353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Automated computer vision systems have been applied in many domains including security, law enforcement, and personal devices, but recent reports suggest that these systems may produce biased results, discriminating against people in certain demographic groups. Diagnosing and understanding the underlying true causes of model biases, however, are challenging tasks because modern computer vision systems rely on complex black-box models whose behaviors are hard to decode. We propose to use an encoder-decoder network developed for image attribute manipulation to synthesize facial images varying in the dimensions of gender and race while keeping other signals intact. We use these synthesized images to measure counterfactual fairness of commercial computer vision classifiers by examining the degree to which these classifiers are affected by gender and racial cues controlled in the images, e.g., feminine faces may elicit higher scores for the concept of nurse and lower scores for STEM-related concepts.
{"title":"Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation","authors":"Jungseock Joo, Kimmo Kärkkäinen","doi":"10.1145/3422841.3423533","DOIUrl":"https://doi.org/10.1145/3422841.3423533","url":null,"abstract":"Automated computer vision systems have been applied in many domains including security, law enforcement, and personal devices, but recent reports suggest that these systems may produce biased results, discriminating against people in certain demographic groups. Diagnosing and understanding the underlying true causes of model biases, however, are challenging tasks because modern computer vision systems rely on complex black-box models whose behaviors are hard to decode. We propose to use an encoder-decoder network developed for image attribute manipulation to synthesize facial images varying in the dimensions of gender and race while keeping other signals intact. We use these synthesized images to measure counterfactual fairness of commercial computer vision classifiers by examining the degree to which these classifiers are affected by gender and racial cues controlled in the images, e.g., feminine faces may elicit higher scores for the concept of nurse and lower scores for STEM-related concepts.","PeriodicalId":428850,"journal":{"name":"Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115957766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia","authors":"","doi":"10.1145/3422841","DOIUrl":"https://doi.org/10.1145/3422841","url":null,"abstract":"","PeriodicalId":428850,"journal":{"name":"Proceedings of the 2nd International Workshop on Fairness, Accountability, Transparency and Ethics in Multimedia","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116342555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：