Mayra Russo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Mayra Russo has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Maria-Esther Vidal
TIB Leibniz Information Centre for Science and Technology
5 shared publications - Kristen M. Scott
KU Leuven, Belgium
4 shared publications - Miriam Fahimi
University of Klagenfurt, Klagenfurt, Austria
3 shared publications - Anaelia Ovalle
University of California Los Angeles † {elaine1wan
2 shared publications - Antonio Ferrara
Intesa Sanpaolo AI Research, Turin, Italy and TU Graz, Graz, Austria
2 shared publications - Avijit Ghosh
Hugging Face, New York, USA
2 shared publications
Latest Publications
- 28 August 2025
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 83
Towards an Ontology-Driven Approach to Document Bias
Machine learning (ML)-powered systems are capable of reproducing and often amplifying undesired biases embedded in society, emphasizing the importance of operating under practices that enable the study and understanding of the intrinsic characteristics of ML pipelines. This supports the emergence of documentation frameworks with the idea that “any remedy for bias starts with awareness of its existence.” However, a resource that can formally describe ML pipelines in terms of detected biases is still missing. To address this gap, we present the Doc-BiasO ontology, a resource that sets out to create an integrated vocabulary of biases defined in the Trustworthy AI literature and their measures, as well as to incorporate relevant domain terminology and relationships between them. Overseeing ontology engineering best practices, we reuse existing vocabularies on machine learning and AI to foster knowledge sharing and interoperability between the actors concerned with its research, development, regulation, and others. In addition, we demonstrate the potential of Doc-BiasO with an experiment on an existing benchmark and as part of a neuro-symbolic system. Overall, our main objective is to contribute towards clarifying existing terminology on bias research as it rapidly expands to all areas of AI and to improve the interpretation of bias in data and downstream impact through its documentation.
- 28 August 2025
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 83
Towards an Ontology-Driven Approach to Document Bias
Machine learning (ML)-powered systems are capable of reproducing and often amplifying undesired biases embedded in society, emphasizing the importance of operating under practices that enable the study and understanding of the intrinsic characteristics of ML pipelines. This supports the emergence of documentation frameworks with the idea that “any remedy for bias starts with awareness of its existence.” However, a resource that can formally describe ML pipelines in terms of detected biases is still missing. To address this gap, we present the Doc-BiasO ontology, a resource that sets out to create an integrated vocabulary of biases defined in the Trustworthy AI literature and their measures, as well as to incorporate relevant domain terminology and relationships between them. Overseeing ontology engineering best practices, we reuse existing vocabularies on machine learning and AI to foster knowledge sharing and interoperability between the actors concerned with its research, development, regulation, and others. In addition, we demonstrate the potential of Doc-BiasO with an experiment on an existing benchmark and as part of a neuro-symbolic system. Overall, our main objective is to contribute towards clarifying existing terminology on bias research as it rapidly expands to all areas of AI and to improve the interpretation of bias in data and downstream impact through its documentation.
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2670-2679
Tracing Bias for Fairer Content-Based Misinformation Detection
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2670-2679
Open AccessTracing Bias for Fairer Content-Based Misinformation Detection
- Open Access
- 7 November 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW2) , 1-23
Articulation Work and Tinkering for Fairness in Machine Learning
The field of fair AI aims to counter biased algorithms through computational modelling. However, it faces increasing criticism for perpetuating the use of overly technical and reductionist methods. As a result, novel approaches appear in the field to address more socially-oriented and interdisciplinary (SOI) perspectives on fair AI. In this paper, we take this dynamic as the starting point to study the tension between computer science (CS) and SOI research. By drawing on STS and CSCW theory, we position fair AI research as a matter of 'organizational alignment': what makes research 'doable' is the successful alignment of three levels of work organization (the social world, the laboratory, and the experiment). Based on qualitative interviews with CS researchers, we analyze the tasks, resources, and actors required for doable research in the case of fair AI. We find that CS researchers engage with SOI research to some extent, but organizational conditions, articulation work, and ambiguities of the social world constrain the doability of SOI research for them. Based on our findings, we identify and discuss problems for aligning CS and SOI as fair AI continues to evolve.
- 7 November 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (CSCW2) , 1-23
Open AccessArticulation Work and Tinkering for Fairness in Machine Learning
The field of fair AI aims to counter biased algorithms through computational modelling. However, it faces increasing criticism for perpetuating the use of overly technical and reductionist methods. As a result, novel approaches appear in the field to address more socially-oriented and interdisciplinary (SOI) perspectives on fair AI. In this paper, we take this dynamic as the starting point to study the tension between computer science (CS) and SOI research. By drawing on STS and CSCW theory, we position fair AI research as a matter of 'organizational alignment': what makes research 'doable' is the successful alignment of three levels of work organization (the social world, the laboratory, and the experiment). Based on qualitative interviews with CS researchers, we analyze the tasks, resources, and actors required for doable research in the case of fair AI. We find that CS researchers engage with SOI research to some extent, but organizational conditions, articulation work, and ambiguities of the social world constrain the doability of SOI research for them. Based on our findings, we identify and discuss problems for aligning CS and SOI as fair AI continues to evolve.
- Open Access
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Bridging Research and Practice Through Conversation: Reflecting on Our Experience
While some research fields have a long history of collaborating with domain experts outside academia, many quantitative researchers do not have natural avenues to meet experts in areas where the research is later deployed. We explain how conversations—interviews without a specific research objective—can bridge research and practice. Using collaborative autoethnography, we reflect on our experience of conducting conversations with practitioners from a range of different backgrounds, including refugee rights, conservation, addiction counseling, and municipal data science. Despite these varied backgrounds, common lessons emerged, including the importance of valuing the knowledge of experts, recognizing that academic research and practice have differing objectives and timelines, understanding the limits of quantification, and avoiding data extractivism. We consider the impact of these conversations on our work, the potential roles we can serve as researchers, and the challenges we anticipate as we move forward in these collaborations.
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessBridging Research and Practice Through Conversation: Reflecting on Our Experience
While some research fields have a long history of collaborating with domain experts outside academia, many quantitative researchers do not have natural avenues to meet experts in areas where the research is later deployed. We explain how conversations—interviews without a specific research objective—can bridge research and practice. Using collaborative autoethnography, we reflect on our experience of conducting conversations with practitioners from a range of different backgrounds, including refugee rights, conservation, addiction counseling, and municipal data science. Despite these varied backgrounds, common lessons emerged, including the importance of valuing the knowledge of experts, recognizing that academic research and practice have differing objectives and timelines, understanding the limits of quantification, and avoiding data extractivism. We consider the impact of these conversations on our work, the potential roles we can serve as researchers, and the challenges we anticipate as we move forward in these collaborations.
- Open Access
- 12 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 96821-96847
Employing Hybrid AI Systems to Trace and Document Bias in ML Pipelines
Artificial Intelligence (AI) systems can introduce biases that lead to unreliable outcomes and, in the worst-case scenarios, perpetuate systemic and discriminatory results when deployed in the real world. While significant efforts have been made to create bias detection methods, developing reliable and comprehensive documentation artifacts also makes for valuable resources that address bias and aid in minimizing the harms associated with AI systems. Based on compositional design patterns, this paper introduces a documentation approach using a hybrid AI system to prompt the identification and traceability of bias in datasets and predictive AI models. To demonstrate the effectiveness of our approach, we instantiate our pattern in two implementations of a hybrid AI system. One follows an integrated approach and performs fine-grained tracing and documentation of the AI model. In contrast, the other hybrid system follows a principled approach and enables the documentation and comparison of bias in the input data and the predictions generated by the model. Through a use-case based on Fake News detection and an empirical evaluation, we show how biases detected during data ingestion steps (e.g., label, over-representation, activity bias) affect the training and predictions of the classification models. Concretely, we report a stark skewness in the distribution of input variables towards the Fake News label, we uncover how a predictive variable leads to more constraints in the learning process, and highlight open challenges of training models with unbalanced datasets. A video summarizing this work is available online ( https://youtu.be/v2GfIQPAy_4?si=BXtWOf97cLiZavyu ),and the implementation is publicly available on GitHub ( https://github.com/SDM-TIB/DocBiasKG ).
- 12 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 96821-96847
Open AccessEmploying Hybrid AI Systems to Trace and Document Bias in ML Pipelines
Artificial Intelligence (AI) systems can introduce biases that lead to unreliable outcomes and, in the worst-case scenarios, perpetuate systemic and discriminatory results when deployed in the real world. While significant efforts have been made to create bias detection methods, developing reliable and comprehensive documentation artifacts also makes for valuable resources that address bias and aid in minimizing the harms associated with AI systems. Based on compositional design patterns, this paper introduces a documentation approach using a hybrid AI system to prompt the identification and traceability of bias in datasets and predictive AI models. To demonstrate the effectiveness of our approach, we instantiate our pattern in two implementations of a hybrid AI system. One follows an integrated approach and performs fine-grained tracing and documentation of the AI model. In contrast, the other hybrid system follows a principled approach and enables the documentation and comparison of bias in the input data and the predictions generated by the model. Through a use-case based on Fake News detection and an empirical evaluation, we show how biases detected during data ingestion steps (e.g., label, over-representation, activity bias) affect the training and predictions of the classification models. Concretely, we report a stark skewness in the distribution of input variables towards the Fake News label, we uncover how a predictive variable leads to more constraints in the learning process, and highlight open challenges of training models with unbalanced datasets. A video summarizing this work is available online ( https://youtu.be/v2GfIQPAy_4?si=BXtWOf97cLiZavyu ),and the implementation is publicly available on GitHub ( https://github.com/SDM-TIB/DocBiasKG ).
- Open Access
- 29 April 2024
- Published by Springer Nature in Ethics and Information Technology
- Vol. 26 (2) , 1-26
Policy advice and best practices on bias and fairness in AI
The literature addressing bias and fairness in AI models (fair-AI) is growing at a fast pace, making it difficult for novel researchers and practitioners to have a bird’s-eye view picture of the field. In particular, many policy initiatives, standards, and best practices in fair-AI have been proposed for setting principles, procedures, and knowledge bases to guide and operationalize the management of bias and fairness. The first objective of this paper is to concisely survey the state-of-the-art of fair-AI methods and resources, and the main policies on bias in AI, with the aim of providing such a bird’s-eye guidance for both researchers and practitioners. The second objective of the paper is to contribute to the policy advice and best practices state-of-the-art by leveraging from the results of the NoBIAS research project. We present and discuss a few relevant topics organized around the NoBIAS architecture, which is made up of a Legal Layer, focusing on the European Union context, and a Bias Management Layer, focusing on understanding, mitigating, and accounting for bias.
- 29 April 2024
- Published by Springer Nature in Ethics and Information Technology
- Vol. 26 (2) , 1-26
Open AccessPolicy advice and best practices on bias and fairness in AI
The literature addressing bias and fairness in AI models (fair-AI) is growing at a fast pace, making it difficult for novel researchers and practitioners to have a bird’s-eye view picture of the field. In particular, many policy initiatives, standards, and best practices in fair-AI have been proposed for setting principles, procedures, and knowledge bases to guide and operationalize the management of bias and fairness. The first objective of this paper is to concisely survey the state-of-the-art of fair-AI methods and resources, and the main policies on bias in AI, with the aim of providing such a bird’s-eye guidance for both researchers and practitioners. The second objective of the paper is to contribute to the policy advice and best practices state-of-the-art by leveraging from the results of the NoBIAS research project. We present and discuss a few relevant topics organized around the NoBIAS architecture, which is made up of a Legal Layer, focusing on the European Union context, and a Bias Management Layer, focusing on understanding, mitigating, and accounting for bias.
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1626-1633
Tracing the Impact of Bias in Link Prediction
Link prediction (LP) in knowledge graphs (KGs) uses embedding-based approaches and machine learning (ML) models to uncover new facts. In order to not overstate and accurately assess the performance of these techniques, their comprehensive and rigorous evaluation is needed. In this work, we suggest a framework to systematically trace and analyze bias---specifically, test leakage bias and sample selection bias---in training and testing knowledge graphs (KGs). The goal is to evaluate how bias affects the performance of LP models We specify a collection of bias measures in SPARQL (the W3C standard query language) to facilitate the analysis of any RDF graph with regard to its structural bias properties. Further, we evaluate our framework over seven state-of-the-art LP datasets (e.g., FB15k-237, WN18RR, and YAGO3-10) and the TransE model. Our findings show how bias, i.e., overrepresentation of entities and relations and pronounced information redundancy, is present across all datasets and how it advantageously impacts the reported performance of the LP model. With these results, we make a call for thorough assessments of data sources in order to discourage the use of biased datasets when appropriate, and to also help improve our understanding of how LP models work and to better interpret their produced output.
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1626-1633
Open AccessTracing the Impact of Bias in Link Prediction
Link prediction (LP) in knowledge graphs (KGs) uses embedding-based approaches and machine learning (ML) models to uncover new facts. In order to not overstate and accurately assess the performance of these techniques, their comprehensive and rigorous evaluation is needed. In this work, we suggest a framework to systematically trace and analyze bias---specifically, test leakage bias and sample selection bias---in training and testing knowledge graphs (KGs). The goal is to evaluate how bias affects the performance of LP models We specify a collection of bias measures in SPARQL (the W3C standard query language) to facilitate the analysis of any RDF graph with regard to its structural bias properties. Further, we evaluate our framework over seven state-of-the-art LP datasets (e.g., FB15k-237, WN18RR, and YAGO3-10) and the TransE model. Our findings show how bias, i.e., overrepresentation of entities and relations and pronounced information redundancy, is present across all datasets and how it advantageously impacts the reported performance of the LP model. With these results, we make a call for thorough assessments of data sources in order to discourage the use of biased datasets when appropriate, and to also help improve our understanding of how LP models work and to better interpret their produced output.
- Open Access
- 6 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 121-125
A Multidisciplinary Lens of Bias in Hate Speech
Hate speech detection systems may exhibit discriminatory behaviours. Research in this field has focused primarily on issues of discrimination toward the language use of minoritised communities and non-White aligned English. The interrelated issues of bias, model robustness, and disproportionate harms are weakly addressed by recent evaluation approaches, which capture them only implicitly. In this paper, we recruit a multidisciplinary group of experts to bring closer this divide between fairness and trustworthy model evaluation. Specifically, we encourage the experts to discuss not only the technical, but the social, ethical, and legal aspects of this timely issue. The discussion sheds light on critical bias facets that require careful considerations when deploying hate speech detection systems in society. Crucially, they bring clarity to different approaches for assessing, becoming aware of bias from a broader perspective, and offer valuable recommendations for future research in this field.
- 6 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 121-125
Open AccessA Multidisciplinary Lens of Bias in Hate Speech
Hate speech detection systems may exhibit discriminatory behaviours. Research in this field has focused primarily on issues of discrimination toward the language use of minoritised communities and non-White aligned English. The interrelated issues of bias, model robustness, and disproportionate harms are weakly addressed by recent evaluation approaches, which capture them only implicitly. In this paper, we recruit a multidisciplinary group of experts to bring closer this divide between fairness and trustworthy model evaluation. Specifically, we encourage the experts to discuss not only the technical, but the social, ethical, and legal aspects of this timely issue. The discussion sheds light on critical bias facets that require careful considerations when deploying hate speech detection systems in society. Crucially, they bring clarity to different approaches for assessing, becoming aware of bias from a broader perspective, and offer valuable recommendations for future research in this field.
- Open Access
- 8 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 375-386
Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
Bias evaluation benchmarks and dataset and model documentation have emerged as central processes for assessing the biases and harms of artificial intelligence (AI) systems. However, these auditing processes have been criticized for their failure to integrate the knowledge of marginalized communities and consider the power dynamics between auditors and the communities. Consequently, modes of bias evaluation have been proposed that engage impacted communities in identifying and assessing the harms of AI systems (e.g., bias bounties). Even so, asking what marginalized communities want from such auditing processes has been neglected. In this paper, we ask queer communities for their positions on, and desires from, auditing processes. To this end, we organized a participatory workshop to critique and redesign bias bounties from queer perspectives. We found that when given space, the scope of feedback from workshop participants goes far beyond what bias bounties afford, with participants questioning the ownership, incentives, and efficacy of bounties. We conclude by advocating for community ownership of bounties and complementing bounties with participatory processes (e.g., co-creation).
- 8 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 375-386
Open AccessBound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
Bias evaluation benchmarks and dataset and model documentation have emerged as central processes for assessing the biases and harms of artificial intelligence (AI) systems. However, these auditing processes have been criticized for their failure to integrate the knowledge of marginalized communities and consider the power dynamics between auditors and the communities. Consequently, modes of bias evaluation have been proposed that engage impacted communities in identifying and assessing the harms of AI systems (e.g., bias bounties). Even so, asking what marginalized communities want from such auditing processes has been neglected. In this paper, we ask queer communities for their positions on, and desires from, auditing processes. To this end, we organized a participatory workshop to critique and redesign bias bounties from queer perspectives. We found that when given space, the scope of feedback from workshop participants goes far beyond what bias bounties afford, with participants questioning the ownership, incentives, and efficacy of bounties. We conclude by advocating for community ownership of bounties and complementing bounties with participatory processes (e.g., co-creation).
- Open Access
Bound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
Bias evaluation benchmarks and dataset and model documentation have emerged as central processes for assessing the biases and harms of artificial intelligence (AI) systems. However, these auditing processes have been criticized for their failure to integrate the knowledge of marginalized communities and consider the power dynamics between auditors and the communities. Consequently, modes of bias evaluation have been proposed that engage impacted communities in identifying and assessing the harms of AI systems (e.g., bias bounties). Even so, asking what marginalized communities want from such auditing processes has been neglected. In this paper, we ask queer communities for their positions on, and desires from, auditing processes. To this end, we organized a participatory workshop to critique and redesign bias bounties from queer perspectives. We found that when given space, the scope of feedback from workshop participants goes far beyond what bias bounties afford, with participants questioning the ownership, incentives, and efficacy of bounties. We conclude by advocating for community ownership of bounties and complementing bounties with participatory processes (e.g., co-creation).
Open AccessBound by the Bounty: Collaboratively Shaping Evaluation Processes for Queer AI Harms
Bias evaluation benchmarks and dataset and model documentation have emerged as central processes for assessing the biases and harms of artificial intelligence (AI) systems. However, these auditing processes have been criticized for their failure to integrate the knowledge of marginalized communities and consider the power dynamics between auditors and the communities. Consequently, modes of bias evaluation have been proposed that engage impacted communities in identifying and assessing the harms of AI systems (e.g., bias bounties). Even so, asking what marginalized communities want from such auditing processes has been neglected. In this paper, we ask queer communities for their positions on, and desires from, auditing processes. To this end, we organized a participatory workshop to critique and redesign bias bounties from queer perspectives. We found that when given space, the scope of feedback from workshop participants goes far beyond what bias bounties afford, with participants questioning the ownership, incentives, and efficacy of bounties. We conclude by advocating for community ownership of bounties and complementing bounties with participatory processes (e.g., co-creation).