{"type":"ScholarlyArticle","title":"Addressing Age-Related Bias in Sentiment Analysis","authors":[{"name":"Mark Díaz","slug":"mark-diaz","given":"Mark","family":"Díaz","affiliation":"Northwestern University"},{"name":"Isaac Johnson","slug":"isaac-johnson","given":"Isaac","family":"Johnson","affiliation":"Northwestern University"},{"name":"Amanda Lazar","slug":"amanda-lazar","given":"Amanda","family":"Lazar","affiliation":"University of Maryland"},{"name":"Anne Marie Piper","slug":"anne-marie-piper","given":"Anne Marie","family":"Piper","affiliation":"Northwestern University"},{"name":"Darren Gergle","slug":"darren-gergle","given":"Darren","family":"Gergle","affiliation":"Northwestern University"}],"abstract":"Recent studies have identified various forms of bias in language-based models, raising concerns about the risk of propagating social biases against certain groups based on sociodemographic factors (e.g., gender, race, geography). In this study, we analyze the treatment of age-related terms across 15 sentiment analysis models and 10 widely-used GloVe word embeddings and attempt to alleviate bias through a method of processing model training data. Our results show significant age bias is encoded in the outputs of many sentiment analysis algorithms and word embeddings, and we can alleviate this bias by manipulating training data.","doi":"10.24963/ijcai.2019/852","url":"https://ijcai.org/proceedings/2019/852","pdf":"https://ijcai.org/proceedings/2019/0852.pdf","markdown":"https://ijcai.org/proceedings/2019/852.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/852","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Best Sister Conferences","track":"Best Sister Conferences","number":852,"pages":{"first":6146,"last":6150},"keywords":["Multidisciplinary Topics and Applications: Social Sciences","Natural Language Processing: Sentiment Analysis and Text Mining","Humans and AI: Ethical Issues in AI"],"videos":[],"references":[{"position":1,"raw":"[Baker and Potts, 2013] Paul Baker and Amanda Potts. 'why do white people have thin lips?'google and the perpetua- tion of stereotypes via auto-complete search forms. Criti- cal Discourse Studies, 10(2):187-204, 2013.","title":"why do white people have thin lips?'google and the perpetuation of stereotypes via auto-complete search forms","authors":"Potts Baker, Paul Baker, Amanda Potts","year":"2013","venue":"Critical Discourse Studies","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bolukbasi et al., 2016] Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. Quan- tifying and reducing stereotypes in word embeddings. arXiv preprint arXiv:1606.06121, 2016.","title":"Quantifying and reducing stereotypes in word embeddings","authors":"Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, Adam Kalai","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Brewer et al., 2016] Robin Brewer, Meredith Ringel Mor- ris, and Anne Marie Piper. Why would anybody do this?: Understanding older adults' motivations and challenges in crowd work. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pages 2246- 2257. ACM, 2016.","title":"Why would anybody do this?: Understanding older adults' motivations and challenges in crowd work","authors":"Brewer","year":"2016","venue":"Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Caliskan et al., 2017] Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334):183-186, 2017.","title":"Semantics derived automatically from language corpora contain human-like biases","authors":"Aylin Caliskan, Joanna J Bryson, Arvind Narayanan","year":"2017","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2015] Le Chen, Alan Mislove, and Christo Wil- son. Peeking beneath the hood of uber. In Proceedings of the 2015 Internet Measurement Conference, pages 495- 508. ACM, 2015.","title":"Peeking beneath the hood of uber","authors":"Le Chen, Alan Mislove, Christo Wilson","year":"2015","venue":"Proceedings of the 2015 Internet Measurement Conference","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Crenshaw, 1990] Kimberle Crenshaw. Mapping the mar- gins: Intersectionality, identity politics, and violence against women of color. Stan. L. Rev., 43:1241, 1990.","title":"Kimberle Crenshaw. Mapping the margins: Intersectionality, identity politics, and violence against women of color","authors":"Crenshaw","year":"1990","venue":"Stan. L. Rev","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Diakopoulos, 2014] Nicholas Diakopoulos. Algorithmic accountability reporting: On the investigation of black boxes. 2014.","title":"Algorithmic accountability reporting: On the investigation of black boxes","authors":"Nicholas Diakopoulos","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Díaz et al., 2018] Mark Díaz, Isaac Johnson, Amanda Lazar, Anne Marie Piper, and Darren Gergle. Address- ing age-related bias in sentiment analysis. In Proceedings of the 2018 CHI Conference on Human Factors in Com- puting Systems, page 412. ACM, 2018.","title":"Addressing age-related bias in sentiment analysis","authors":"Mark Díaz, Isaac Johnson, Amanda Lazar, Anne Marie Piper, Darren Gergle","year":"2018","venue":"Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Feldman, 2013] Ronen Feldman. Techniques and applica- tions for sentiment analysis. Communications of the ACM, 56(4):82-89, 2013.","title":"Techniques and applications for sentiment analysis","authors":"Ronen Feldman, Feldman","year":"2013","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Friedman and Nissenbaum, 1996] Batya Friedman and He- len Nissenbaum. Bias in computer systems. ACM Trans- actions on Information Systems (TOIS), 14(3):330-347, 1996.","title":"Bias in computer systems","authors":"Nissenbaum ; Friedman, Helen Friedman, Nissenbaum","year":"1996","venue":"ACM Transactions on Information Systems (TOIS)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hu and Liu, 2004] Minqing Hu and Bing Liu. Mining and summarizing customer reviews. In Proceedings of the tenth ACM SIGKDD international conference on Knowl- edge discovery and data mining, pages 168-177. ACM, 2004.","title":"Mining and summarizing customer reviews","authors":"Liu Hu, Minqing Hu, Bing Liu","year":"2004","venue":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Johnson et al., 2017] Isaac Johnson, Connor McMahon, Jo- hannes Schöning, and Brent Hecht. The effect of pop- ulation and structural biases on social media-based al- gorithms: A case study in geolocation inference across the urban-rural spectrum. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Sys- tems, pages 1167-1178. ACM, 2017.","title":"The effect of population and structural biases on social media-based algorithms: A case study in geolocation inference across the urban-rural spectrum","authors":"Johnson","year":"2017","venue":"Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kay et al., 2015] Matthew Kay, Cynthia Matuszek, and Sean A Munson. Unequal representation and gender stereotypes in image search results for occupations. In Proceedings of the 33rd Annual ACM Conference on Hu- man Factors in Computing Systems, pages 3819-3828. ACM, 2015.","title":"Unequal representation and gender stereotypes in image search results for occupations","authors":"Kay","year":"2015","venue":"Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lahey, 2010] Joanna N Lahey. International comparison of age discrimination laws. Research on aging, 32(6):679- 697, 2010.","title":"International comparison of age discrimination laws","authors":"Joanna N Lahey","year":"2010","venue":"Research on aging","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lazar et al., 2017] Amanda Lazar, Mark Diaz, Robin Brewer, Chelsea Kim, and Anne Marie Piper. Going gray, failure to hire, and the ick factor: Analyzing how older bloggers talk about ageism. In Proceedings of the 2017 ACM Conference on Computer Supported Coopera- tive Work and Social Computing, pages 655-668. ACM, 2017.","title":"Going gray, failure to hire, and the ick factor: Analyzing how older bloggers talk about ageism","authors":"Amanda Lazar, Mark Diaz, Robin Brewer, Chelsea Kim, Anne Marie Piper","year":"2017","venue":"Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mark, 2008] Davies Mark. The corpus of contempo- rary american english (coca): 520 million words, 1990- present, 2008.","title":"The corpus of contemporary american english (coca): 520 million words, 1990present","authors":"Davies Mark","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nissenbaum, 2001] Helen Nissenbaum. How computer sys- tems embody values. Computer, 34(3):120-119, 2001.","title":"How computer systems embody values","authors":"Helen Nissenbaum","year":"2001","venue":"Computer","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher Manning. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher Manning","year":"2014","venue":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ribeiro et al., 2016] Filipe N Ribeiro, Matheus Araújo, Pollyanna Gonçalves, Marcos André Gonçalves, and Fab- rício Benevenuto. Sentibench-a benchmark comparison of state-of-the-practice sentiment analysis methods. EPJ Data Science, 5(1):1-29, 2016.","title":"Sentibench-a benchmark comparison of state-of-the-practice sentiment analysis methods","authors":"Matheus Filipe N Ribeiro, Pollyanna Araújo, Marcos André Gonçalves, Fabrício Gonçalves, Benevenuto","year":"2016","venue":"EPJ Data Science","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sen et al., 2015] Shilad Sen, Margaret E Giesel, Rebecca Gold, Benjamin Hillmann, Matt Lesicko, Samuel Naden, Jesse Russell, Zixiao Ken Wang, and Brent Hecht. Turk- ers, scholars, arafat and peace: Cultural communities and algorithmic gold standards. In Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing, pages 826-838. ACM, 2015.","title":"Turkers, scholars, arafat and peace: Cultural communities and algorithmic gold standards","authors":"Sen","year":"2015","venue":"Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Socher et al., 2013] Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Ng, and Christopher Potts. Recursive deep models for seman- tic compositionality over a sentiment treebank. In Pro- ceedings of the 2013 conference on empirical methods in natural language processing, pages 1631-1642, 2013.","title":"Recursive deep models for semantic compositionality over a sentiment treebank","authors":"Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Ng, Christopher Potts","year":"2013","venue":"Proceedings of the 2013 conference on empirical methods in natural language processing","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sweeney, 2013] Latanya Sweeney. Discrimination in online ad delivery. arXiv preprint arXiv:1301.6822, 2013.","title":"Discrimination in online ad delivery","authors":"Latanya Sweeney","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Taboada et al., 2011] Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll, and Manfred Stede. Lexicon- based methods for sentiment analysis. Computational lin- guistics, 37(2):267-307, 2011.","title":"Lexiconbased methods for sentiment analysis","authors":"Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll, Manfred Stede","year":"2011","venue":"Computational linguistics","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wagner et al., 2016] Claudia Wagner, Eduardo Graells- Garrido, David Garcia, and Filippo Menczer. Women through the glass ceiling: gender asymmetries in wikipedia. EPJ Data Science, 5(1):5, 2016.","title":"Women through the glass ceiling: gender asymmetries in wikipedia","authors":"Claudia Wagner, Eduardo Graells-Garrido, David Garcia, Filippo Menczer","year":"2016","venue":"EPJ Data Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}