{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/140992"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/140992","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Towards Human-Centered Optimality Criteria","abstract":"Despite the transformational success of machine learning across various applications, examples of deployed models failing to recognize and support human-centered (HC) criteria are abundant. In this thesis, I conceptualize the space of human-machine collaboration with respect to two components: interpretation of people by machines and interpretation of machines by people. I develop several tools that make improvements along these axes. First, I develop a pipeline that predicts depressive symptoms rated by clinicians from real-world longitudinal data outperforming several baselines. Second, I introduce a novel, model-agnostic, and dataset-agnostic method to approximate interactive human evaluation in open-domain dialog through self-play that is more strongly correlated with human evaluations than other automated metrics commonly used today. While dialog quality evaluation metrics predominantly use word-level overlap or distance metrics based on embedding resemblance to each turn of the conversation, I show the significance of taking into account the conversation's trajectory and using proxies such as sentiment, semantics, and user engagement that are psychologically motivated. Third, I demonstrate an uncertainty measurement technique that helps disambiguate annotator disagreement and data bias. I show that this characterization also improves model performance. Finally, I present a novel method that allows humans to investigate a predictor's decision-making process to gain better insight into how it works. The method jointly trains a generator, a discriminator, and a concept disentangler, allowing the human to ask \"what-if\" questions. I evaluate it on several challenging synthetic and realistic datasets where previous methods fall short of satisfying desirable criteria for interpretability and show that our method performs consistently well across all. I discuss its applications to detect potential biases of a classifier and identify spurious artifacts that impact predictions using simulated experiments. Together, these novel techniques and insights provide a more comprehensive interpretation of people by machines and more powerful tools for interpretation of machines by people that can move us closer to HC optimality.","abstract_html":"Despite the transformational success of machine learning across various applications, examples of deployed models failing to recognize and support human-centered (HC) criteria are abundant. In this thesis, I conceptualize the space of human-machine collaboration with respect to two components: interpretation of people by machines and interpretation of machines by people. I develop several tools that make improvements along these axes. First, I develop a pipeline that predicts depressive symptoms rated by clinicians from real-world longitudinal data outperforming several baselines. Second, I introduce a novel, model-agnostic, and dataset-agnostic method to approximate interactive human evaluation in open-domain dialog through self-play that is more strongly correlated with human evaluations than other automated metrics commonly used today. While dialog quality evaluation metrics predominantly use word-level overlap or distance metrics based on embedding resemblance to each turn of the conversation, I show the significance of taking into account the conversation's trajectory and using proxies such as sentiment, semantics, and user engagement that are psychologically motivated. Third, I demonstrate an uncertainty measurement technique that helps disambiguate annotator disagreement and data bias. I show that this characterization also improves model performance. Finally, I present a novel method that allows humans to investigate a predictor's decision-making process to gain better insight into how it works. The method jointly trains a generator, a discriminator, and a concept disentangler, allowing the human to ask "what-if" questions. I evaluate it on several challenging synthetic and realistic datasets where previous methods fall short of satisfying desirable criteria for interpretability and show that our method performs consistently well across all. I discuss its applications to detect potential biases of a classifier and identify spurious artifacts that impact predictions using simulated experiments. Together, these novel techniques and insights provide a more comprehensive interpretation of people by machines and more powerful tools for interpretation of machines by people that can move us closer to HC optimality.","abstract_has_math":false,"creators":["Ghandeharioun, Asma"],"institution":"Massachusetts Institute of Technology","degree_name":"Doctoral","degree_level":null,"degree_discipline":null,"degree_department":"Program in Media Arts and Sciences (Massachusetts Institute of Technology)","school":null,"contributors":[],"advisors":["Picard, Rosalind W."],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-06","date_published":"2021-06","updated_at":"2026-07-22T22:22:13Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/140992","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Picard, Rosalind W."]},{"key":"dc:contributor.department","label":"Department","values":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)"]},{"key":"dc:creator","label":"Author","values":["Ghandeharioun, Asma"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-03-03T19:29:03Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-03-03T19:29:03Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-06"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctoral","Doctor of Philosophy"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/140992"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Despite the transformational success of machine learning across various applications, examples of deployed models failing to recognize and support human-centered (HC) criteria are abundant. In this thesis, I conceptualize the space of human-machine collaboration with respect to two components: interpretation of people by machines and interpretation of machines by people. I develop several tools that make improvements along these axes. First, I develop a pipeline that predicts depressive symptoms rated by clinicians from real-world longitudinal data outperforming several baselines. Second, I introduce a novel, model-agnostic, and dataset-agnostic method to approximate interactive human evaluation in open-domain dialog through self-play that is more strongly correlated with human evaluations than other automated metrics commonly used today. While dialog quality evaluation metrics predominantly use word-level overlap or distance metrics based on embedding resemblance to each turn of the conversation, I show the significance of taking into account the conversation's trajectory and using proxies such as sentiment, semantics, and user engagement that are psychologically motivated. Third, I demonstrate an uncertainty measurement technique that helps disambiguate annotator disagreement and data bias. I show that this characterization also improves model performance. Finally, I present a novel method that allows humans to investigate a predictor's decision-making process to gain better insight into how it works. The method jointly trains a generator, a discriminator, and a concept disentangler, allowing the human to ask \"what-if\" questions. I evaluate it on several challenging synthetic and realistic datasets where previous methods fall short of satisfying desirable criteria for interpretability and show that our method performs consistently well across all. I discuss its applications to detect potential biases of a classifier and identify spurious artifacts that impact predictions using simulated experiments. Together, these novel techniques and insights provide a more comprehensive interpretation of people by machines and more powerful tools for interpretation of machines by people that can move us closer to HC optimality."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["Towards Human-Centered Optimality Criteria"]}]}],"canonical_facts":{"dc:contributor.advisor":["Picard, Rosalind W."],"dc:contributor.department":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)"],"dc:creator":["Ghandeharioun, Asma"],"dc:date.accessioned":["2022-03-03T19:29:03Z"],"dc:date.available":["2022-03-03T19:29:03Z"],"dc:date.issued":["2021-06"],"dc:description.abstract":["Despite the transformational success of machine learning across various applications, examples of deployed models failing to recognize and support human-centered (HC) criteria are abundant. In this thesis, I conceptualize the space of human-machine collaboration with respect to two components: interpretation of people by machines and interpretation of machines by people. I develop several tools that make improvements along these axes. First, I develop a pipeline that predicts depressive symptoms rated by clinicians from real-world longitudinal data outperforming several baselines. Second, I introduce a novel, model-agnostic, and dataset-agnostic method to approximate interactive human evaluation in open-domain dialog through self-play that is more strongly correlated with human evaluations than other automated metrics commonly used today. While dialog quality evaluation metrics predominantly use word-level overlap or distance metrics based on embedding resemblance to each turn of the conversation, I show the significance of taking into account the conversation's trajectory and using proxies such as sentiment, semantics, and user engagement that are psychologically motivated. Third, I demonstrate an uncertainty measurement technique that helps disambiguate annotator disagreement and data bias. I show that this characterization also improves model performance. Finally, I present a novel method that allows humans to investigate a predictor's decision-making process to gain better insight into how it works. The method jointly trains a generator, a discriminator, and a concept disentangler, allowing the human to ask \"what-if\" questions. I evaluate it on several challenging synthetic and realistic datasets where previous methods fall short of satisfying desirable criteria for interpretability and show that our method performs consistently well across all. I discuss its applications to detect potential biases of a classifier and identify spurious artifacts that impact predictions using simulated experiments. Together, these novel techniques and insights provide a more comprehensive interpretation of people by machines and more powerful tools for interpretation of machines by people that can move us closer to HC optimality."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/140992"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Towards Human-Centered Optimality Criteria"],"dc:type":["Thesis"],"thesis:degree_name":["Doctoral","Doctor of Philosophy"]},"updated_at":"2026-07-22T22:22:13Z"}