{"id":19902,"date":"2024-06-06T14:30:21","date_gmt":"2024-06-06T18:30:21","guid":{"rendered":"https:\/\/engineering.jhu.edu\/magazine-archive\/?p=19902"},"modified":"2024-06-10T14:16:41","modified_gmt":"2024-06-10T18:16:41","slug":"algorithms-for-a-fairer-world","status":"publish","type":"post","link":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/","title":{"rendered":"Algorithms for a Fairer World"},"content":{"rendered":"\"Article<\/a>\n

 <\/p>\n

Machine learning technologies hold the potential to revolutionize decision-making. But how can we ensure AI systems are free of bias? Our experts weigh in.<\/strong><\/p>\n

\"decorative<\/a>What’s in a name? Sometimes, more than might be expected. Assistant Professor of Computer Science Anjalie Field<\/a> has shown that something as seemingly innocuous as people\u2019s names can offer insight into how artificial intelligence and machine learning can get it wrong, and by extension, do wrong.<\/p>\n

Last year, Field\u2014a member of the Center for Language and Speech Processing<\/a>\u2014was part of a team of researchers investigating the possible application of natural language processing (NLP) to assist the nation\u2019s network of child protective services agencies in better serving and protecting vulnerable children at risk of abuse or neglect. NLP is a form of artificial intelligence (AI) that processes large datasets of normal human language using rule-based or probabilistic machine learning to contextualize and understand written communication.<\/p>\n

\"headshot<\/a>
Anjalie Field<\/figcaption><\/figure>\n

Protective services agencies\u2019 case workers typically take careful and extensive notes related to every family that enters the system. Typically, those notes are not analyzed in any systematic way to learn how better to respond to and possibly prevent child abuse. In the social services community, there is tremendous interest in using NLP and AI to help better manage the more than 3.6 million calls that come into child protection agencies across the United States each year.<\/p>\n

Field\u2019s research team applied NLP tools to 3.1 million contact notes collected over a 10-year period in an anonymous child protective services agency. They found that the NLP model did a poorer job at recognizing the names of African American individuals, which could potentially include identifying relatives who might support or shelter endangered children, than it did with white individuals. \u201cHere is an unlooked-for area where machine learning can amplify what is already a well-documented racial bias in child protective services without anyone even recognizing the problem,\u201d Field says.<\/p>\n

As AI and machine learning technologies increasingly come to inform decision-making tasks\u2014and in some situations make decisions\u2014 there is increasing concern over issues of justice, equity, and fairness. At the Whiting School, faculty researchers are engaging with the fundamental issue of fairness in artificial intelligence across a wide spectrum of potential uses and misuses. These efforts range from unleashing the newfound power in neural network\u2013based computing to search for and identify existing biases, to combatting the known tendency of machine learning systems to learn and propagate unfair practices.<\/p>\n

Investigate truth and fairness in machine learning and you quickly discover there is more than one aspect to the challenge. Field, whose research focuses on the ethics and social science aspects of NLP, says her work follows three broad directions. \u201cOne of them is computational social science: How can we use language analysis and automated text processing to identify social injustices that already occur in society?\u201d This approach employs machine learning technology as a tool for identifying bias. For instance, Field has used NLP to investigate the language Wikipedia articles use to portray different groups of people. \u201cDo articles about women emphasize their personal lives more than their careers, whereas articles about men talk more about their careers? When you employ these tools to look across all of Wikipedia and compute statistics around the data, you can start to see these kinds of patterns and biases,\u201d she says.<\/p>\n

\u201cDo articles about women emphasize their personal lives more than their careers, whereas articles about men talk more about their careers? When you employ these tools to look across all of Wikipedia and compute statistics around the data, you can start to see these kinds of patterns and biases.\u201d<\/p>\n

–Anjalie Field, assistant professor of computer science<\/em><\/p><\/blockquote>\n

A second line of her research focuses on building technology to address known issues of existing bias, particularly in public service domains. As part of her work looking at child welfare cases, she used NLP to review thousands of case records, categorized by race, for the frequency of certain words and terms, to identify persistent institutional bias. She found differing language, but not enough to provide conclusive evidence of racial bias. \u201cThis is sort of natural language processing for the social good,\u201d is how she describes it.<\/p>\n

The third direction looks at potential ethical issues within AI itself. \u201cSome of that is directly looking at model bias\u2014is it going to favor certain groups of people more than others?\u2014but also issues like access to technology, privacy, and data ownership.\u201d In this broader subject area of bias, it is the data itself that is typically of greatest concern, but Field emphasizes that bad data should never permit bad results. \u201cI think there\u2019s often a narrative in AI that \u2018the data is biased so it\u2019s not our fault\/there\u2019s nothing we can do about it,\u2019 but that\u2019s not true,\u201d she says.<\/p>\n

\"decorative<\/a>Mark Dredze<\/a>, John C. Malone Professor of Computer Science, a pioneer in using AI tools to gain insights into public health challenges ranging from suicide prevention to vaccine refusal and from tobacco use to gun violence, has also found how bad data can work to amplify bad outcomes. He says early missteps in machine learning algorithms\u2014such as when Microsoft\u2019s initial release of a chatbot called Tay had to be shut down after just 16 hours for spewing obscene and racist language it picked up online\u2014highlight the dangers of working with bad data.<\/p>\n

\u201cThe problem is that if we just accept the data and say to the machine, \u2018Learn how to make decisions from the data,\u2019 when there are biases in the data, or biases in the process of how we learn from data, we will produce biased results. That is the essence of the problem of fairness in machine learning algorithms,\u201d Dredze says.<\/p>\n

\"headshot<\/a>
Mark Dredze<\/figcaption><\/figure>\n

This applies to his own research, some of which involves scanning the web to understand how people turn to the internet for medical information and what innate biases they are likely to encounter there. In a recent paper he co-authored, researchers set about evaluating biases in context-dependent health questions, focusing on sexual and reproductive health care queries. They looked at questions that required specific additional information to be properly answered when that information was not provided. For instance, \u201cWhich is the best birth control method for me?\u201d has no single correct answer, as it depends on sex, age, and other factors. Dredze and colleagues found that large language models often will simply provide answers reflecting the majority demographic, as, for example, suggesting oral contraceptives, a solution only available to women, while neglecting to include the use of condoms. This kind of built-in bias is a special concern for individuals who turn to the web as a replacement for traditional health care advice since misinformed answers have potentially detrimental effects on users\u2019 health, Dredze says.<\/p>\n

\u201cThe problem is that if we just accept the data and say to the machine, \u2018Learn how to make decisions from the data,\u2019 when there are biases in the data, or biases in the process of how we learn from data, we will produce biased results. That is the essence of the problem of fairness in machine learning algorithms.\u201d<\/p>\n

–Mark Dredze, professor of computer science<\/em><\/p><\/blockquote>\n

This and his earlier pioneering work in \u201csocial monitoring\u201d\u2014employing machine learning to gain understanding from text published on social media sites\u2014has led him to focus not just on the raw data, but also on how people use the web.<\/p>\n

\u201cI would describe this as a more holistic approach, where we\u2019re actually building systems and paying attention to how people interact with those systems,\u201d he says. \u201cWhere did our data come from? How did we collect it? I have to care about these issues when giving data to the algorithm and figuring out what the algorithm does. But then I also need to account for the fact that a human will interact with us. And humans are going to have their own biases and issues. So maybe it\u2019s not just that the system is biased or unbiased, but it interacts with someone to create a different kind of bias.\u201d<\/p>\n

The Data Decides<\/span><\/h4>\n

\"decorative<\/a>So how do you make sure AI and programs based on NLP such as ChatGPT are fair and free of bias? To understand the nature of the challenge presented requires grasping a fundamental paradigm shift that has occurred. \u201cWhat\u2019s different is that in the traditional ways computers have been used, the programs themselves were the issue\u2014the code made the decision,\u201d explains cybersecurity expert Yinzhi Cao<\/a>, assistant professor of computer science and technical director of the JHU Information Security Institute<\/a>. \u201cFor AI, the most important thing is the data, because AI learns from the data and makes decisions from what it learns.\u201d<\/p>\n

It is that capability of making autonomous decisions that has the potential to be especially unfair, Cao says. His research has recently focused on security, privacy, and fairness analysis of machine learning systems. He notes that these three concerns can overlap in surprising ways.<\/p>\n

\u201cThe final goal may be that we will be able to ask AI to actually perform the diagnosis, but at this stage, we are using it to generate training images that overcome disparities in age and race and gender.\u201d<\/p>\n

–Yinzhi Cao, assistant professor of computer science<\/em><\/p><\/blockquote>\n

\"headshot<\/a>
Yinzhi Cao<\/figcaption><\/figure>\n

Cao was one of a group of researchers to successfully overcome safeguards on two of the better-known text-to-image generative models that use AI to create original images from written prompts. Typically, these art generators are designed with filters to block violent, pornographic, or other objectionable content. But Cao and colleagues showed that the right algorithm could be used to bypass filters and create images that are not simply unsuitable but also could be used to defame or malign individuals \u201clike a politician or famous person being made to look like they\u2019re doing something wrong,\u201d Cao said in a press release announcing the results of the team\u2019s research efforts.<\/p>\n

Cao also conducts research that instructs AI in medical image analysis to augment medical training and diagnosis in the detection of Lyme disease, a project he has worked on in cooperation with colleagues at the Applied Physics Lab<\/a> and the School of Medicine<\/a>. An early symptom in 70% to 80% of people with Lyme disease is the appearance of a distinctive \u201cbull\u2019s-eye rash,\u201d which is usually a single circle of inflamed skin that slowly spreads from the site of the tick bite. In fair-skinned people, and especially in younger people with unblemished skin, it is easily detected. For clinicians, however, the most useful examples are found in skin types where the contrast is not as distinctive and readily apparent. \u201cThe final goal may be that we will be able to ask AI to actually perform the diagnosis, but at this stage, we are using it to generate training images that overcome disparities in age and race and gender,\u201d he says.<\/p>\n

Algorithms are Everywhere<\/span><\/h4>\n

Making AI decisions understandable may first require overcoming a larger challenge. The term algorithm itself raises math anxiety among many since the word is poorly understood. But Ilya Shpitser<\/a>, the John C. Malone Associate Professor of Computer Science whose work focuses on algorithmic fairness in datasets of all types, points out that algorithms are the basis for everyday decision making among many\u2014even if they don\u2019t know it.<\/p>\n

\"Headshot<\/a>
Ilya Shpitser<\/figcaption><\/figure>\n

\u201cWhen doctors diagnose, when judges set bail, they have a sequence of steps they\u2019ve learned that\u2019s considered reasonable,\u201d he says. \u201cRegardless of how they think of it themselves, they are using algorithms, because judicial decisions and diagnosis cannot be arbitrary; they better be systematic. The fact that similar cases are decided in similar ways: That\u2019s what an algorithm really does.\u201d<\/p>\n

Most important for a judge to appropriately set bail or a doctor to accurately make a diagnosis is the need for good, fair, accurate information. In algorithmic decision-making, it all comes down to the data. And in an imperfect world, for any decision, there will be good data, there will be bad data, and most vexingly of all, there will be data we simply don\u2019t have.<\/p>\n

\u201cAny person who works in actual data, real data of any kind, has missing data in their sets, that\u2019s just how it is, basically,\u201d says Shpitser, who cites a common example of data collection in electronic health records, where missing data can be due to a lack of collection such as a patient was never asked about asthma. Or it could come from a lack of documentation, as when a patient was asked about asthma but the response was never recorded in the medical record. \u201cLack of documentation is particularly common when it comes to patients not having symptoms or presenting comorbidities.\u201d In these cases, rather than recording a negative value for each potential symptom or comorbidity, the missing data fields are left blank and only the positive values are recorded, which skews the value of the data, says Shpitser. \u201cThis makes it essentially impossible to differentiate between the lack of a comorbidity, the lack of documentation of a comorbidity, or the lack of data collection regarding the comorbidity.”<\/p>\n

\u201cMy take on algorithmic fairness research is that it\u2019s not our job as researchers to decide what fair is. I think the discussions of fairness need to be discussions in the public square.\u201d<\/p>\n

–Ilya Shpitser, associate professor of computer science<\/em><\/p><\/blockquote>\n

One of the central challenges in creating fair and accurate algorithms then becomes devising sound methods of correcting for data recorded incompletely, incorrectly, or not at all. \u201cI work on data being screwed up,\u201d is how Shpitser describes it. Along the way, he has demonstrated in his research that it is at least theoretically possible to \u201cbreak the cycle of injustice\u201d (in which variables such as gender, race, disability, or other attributes introduce bias) by making optimal but fair decisions. His research employs the methodology of causal inference, which he describes as \u201cmethods to adjust for incomplete, bad, or missing data to allow reliable and fair inferences to be made.\u201d<\/p>\n

Fairness Isn’t an Oracle Concept<\/span><\/h4>\n

In the past few years as AI systems have caught increasing media attention, highly public machine learning misfires have brought scientists and engineers a deeper awareness of both the importance and the difficulty of designing and implementing systems equitably.<\/p>\n

\u201cFor a long time, we said, \u2018Look, the algorithms are math, and math is math,\u2019\u201d says Dredze. \u201cIt was, \u2018Let\u2019s throw the math at this, and it comes up with what it comes up with.\u2019\u201d That attitude no longer applies. \u201cI think we\u2019ve learned a couple things. One is that the math might be math, but the data is not the data: It always has some kind of bias in it. And we need to do something about that.\u201d<\/p>\n

But that may only be the beginning. \u201cThe other thing we\u2019re learning\u2014and maybe there\u2019s a little controversy to this\u2014is that math isn\u2019t just math. Math always has some assumptions to it. The models that you pick always have some assumptions, and for a variety of reasons we might favor certain models that do better on some groups. And so it\u2019s not only a matter of the data; it\u2019s also a matter of the models we build. How do we make our models aware that fairness is a thing? How do we build into the models some measure of fairness?\u201d<\/p>\n

Which points ultimately to issues that transcend both the data and the math.<\/p>\n

\u201cFairness isn\u2019t an Oracle concept,\u201d notes Dredze. \u201cIf you\u2019ve got kids and you\u2019ve ever tried to give them anything, they complain about fairness, right? And you end up telling them that life isn\u2019t fair. Fairness is subjective: that person got a smaller piece of cake, but they had a frosting flower, and you didn\u2019t get a flower.\u201d<\/p>\n

It is, he points out, tremendously challenging to formalize concepts of fairness. \u201cWe can build that into our models and train them to be aware. But who decides what the right definition of fairness is? Think about the most controversial issues in society, like college admissions. Both sides of affirmative action and college admissions are insisting we need to be fair, but they have opposing views as to what that means,\u201d he said.<\/p>\n

All of which suggests that creating algorithms for a fairer world in the end will not be the purview of computer scientists alone.<\/p>\n

\u201cMy take on algorithmic fairness research is that it\u2019s not our job as researchers to decide what fair is. I think the discussions of fairness need to be discussions in the public square,\u201d says Shpitser. \u201cAs an American citizen, I have my own opinions of what policies we should follow, but that\u2019s a different path than wearing my hat as a researcher on algorithmic fairness. In other words, computer scientists are best suited to be the implementers, not the deciders, in notions of what is fair.\u201d<\/p>\n

He continues: \u201cWhenever I give talks about this, I always get questions that try to push me into being some kind of priesthood that decides for people what fairness criteria to use. I really don\u2019t think that is our job. I have as much grounds to advocate for a particular definition of fairness as any other citizen, but the fact that I work in algorithmic fairness doesn\u2019t give me a special advantage. I\u2019m using modern tools, but the questions themselves are much older than that.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"

Machine learning technologies hold the potential to revolutionize decision-making. But how can we ensure AI systems are free of bias? Our experts weigh in.<\/p>\n","protected":false},"author":4,"featured_media":19842,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[28],"tags":[],"class_list":["post-19902","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-features","issue-spring-2024"],"acf":[],"yoast_head":"\nAlgorithms for a Fairer World - JHU Engineering Magazine<\/title>\n<meta name=\"description\" content=\"Hopkins engineers are working to ensure that AI systems are free of bias.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Algorithms for a Fairer World - JHU Engineering Magazine\" \/>\n<meta property=\"og:description\" content=\"Hopkins engineers are working to ensure that AI systems are free of bias.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/\" \/>\n<meta property=\"og:site_name\" content=\"JHU Engineering Magazine\" \/>\n<meta property=\"article:published_time\" content=\"2024-06-06T18:30:21+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-06-10T18:16:41+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2024\/05\/fairer-world-crop-scaled.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2560\" \/>\n\t<meta property=\"og:image:height\" content=\"1182\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Abby Lattes\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Abby Lattes\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"14 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/\"},\"author\":{\"name\":\"Abby Lattes\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\"},\"headline\":\"Algorithms for a Fairer World\",\"datePublished\":\"2024-06-06T18:30:21+00:00\",\"dateModified\":\"2024-06-10T18:16:41+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/\"},\"wordCount\":2961,\"image\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/fairer-world-crop-scaled.jpg\",\"articleSection\":[\"Features\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/\",\"name\":\"Algorithms for a Fairer World - JHU Engineering Magazine\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/fairer-world-crop-scaled.jpg\",\"datePublished\":\"2024-06-06T18:30:21+00:00\",\"dateModified\":\"2024-06-10T18:16:41+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\"},\"description\":\"Hopkins engineers are working to ensure that AI systems are free of bias.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/#primaryimage\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/fairer-world-crop-scaled.jpg\",\"contentUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/fairer-world-crop-scaled.jpg\",\"width\":2560,\"height\":1182},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2024\\\/06\\\/algorithms-for-a-fairer-world\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Algorithms for a Fairer World\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#website\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/\",\"name\":\"JHU Engineering Magazine\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\",\"name\":\"Abby Lattes\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"caption\":\"Abby Lattes\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Algorithms for a Fairer World - JHU Engineering Magazine","description":"Hopkins engineers are working to ensure that AI systems are free of bias.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/","og_locale":"en_US","og_type":"article","og_title":"Algorithms for a Fairer World - JHU Engineering Magazine","og_description":"Hopkins engineers are working to ensure that AI systems are free of bias.","og_url":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/","og_site_name":"JHU Engineering Magazine","article_published_time":"2024-06-06T18:30:21+00:00","article_modified_time":"2024-06-10T18:16:41+00:00","og_image":[{"width":2560,"height":1182,"url":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2024\/05\/fairer-world-crop-scaled.jpg","type":"image\/jpeg"}],"author":"Abby Lattes","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Abby Lattes","Est. reading time":"14 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/#article","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/"},"author":{"name":"Abby Lattes","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742"},"headline":"Algorithms for a Fairer World","datePublished":"2024-06-06T18:30:21+00:00","dateModified":"2024-06-10T18:16:41+00:00","mainEntityOfPage":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/"},"wordCount":2961,"image":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/#primaryimage"},"thumbnailUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2024\/05\/fairer-world-crop-scaled.jpg","articleSection":["Features"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/","name":"Algorithms for a Fairer World - JHU Engineering Magazine","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#website"},"primaryImageOfPage":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/#primaryimage"},"image":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/#primaryimage"},"thumbnailUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2024\/05\/fairer-world-crop-scaled.jpg","datePublished":"2024-06-06T18:30:21+00:00","dateModified":"2024-06-10T18:16:41+00:00","author":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742"},"description":"Hopkins engineers are working to ensure that AI systems are free of bias.","breadcrumb":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/#primaryimage","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2024\/05\/fairer-world-crop-scaled.jpg","contentUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2024\/05\/fairer-world-crop-scaled.jpg","width":2560,"height":1182},{"@type":"BreadcrumbList","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2024\/06\/algorithms-for-a-fairer-world\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/engineering.jhu.edu\/magazine-archive\/"},{"@type":"ListItem","position":2,"name":"Algorithms for a Fairer World"}]},{"@type":"WebSite","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#website","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/","name":"JHU Engineering Magazine","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/engineering.jhu.edu\/magazine-archive\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742","name":"Abby Lattes","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","caption":"Abby Lattes"}}]}},"_links":{"self":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/19902","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/comments?post=19902"}],"version-history":[{"count":27,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/19902\/revisions"}],"predecessor-version":[{"id":20749,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/19902\/revisions\/20749"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/media\/19842"}],"wp:attachment":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/media?parent=19902"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/categories?post=19902"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/tags?post=19902"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}