{"id":{"repo_id":"toronto-retro","oai_identifier":"oai:utoronto.scholaris.ca:1807/144898"},"canonical_url":"https://search.dev.ndltd.org/etd/toronto-retro/oai:utoronto.scholaris.ca:1807/144898","repository":{"repo_id":"toronto-retro","name":"University of Toronto","base_url":"https://utoronto.scholaris.ca/server/oai/request"},"display":{"title":"Design and Development of a Chatbot as an Alternative Web-browser for those with Severe Motor Impairments","abstract":"Ensuring equitable digital access for individuals with severe motor impairments remains a pressingchallenge. Conventional web navigation relies heavily on manual interactions—pointing, clicking, and typing—that are often inaccessible to users with limited motor function or atypical speech patterns. This research addresses the digital divide by proposing and evaluating two complementary solutions: (1) an eye gaze-controlled chatbot for hands-free, conversational access to online information, and (2) a synthetic data generation approach to improve voice-based chatbot systems’ ability to interpret atypical speech. First, an empirical study involving 20 participants established optimal parameters for eye-gaze target interaction in an Augmented Reality (AR) environment: a 2.25-meter eye-to-target distance and a 0.072-meter Area of Interest (Area of Interest (AOI)) diameter. These parameters achieved target selection rates exceeding 90%. Guided by these findings, the “EyeChat” system integrates an innovative circular text-entry interface that centralizes frequently used keys, reducing unnecessary eye movement. In a subsequent study with 12 participants, EyeChat demonstrated a 4.1-fold increase in text-entry speed (from 2.41 to 9.88 words per minute), a reduction in error rate (from 4.53% to 1.01%), and high user satisfaction, with over 83% of responses meeting or exceeding expectations. Second, to address the needs of individuals who rely on speech-based inputs yet exhibit atypical linguistic patterns, a novel synthetic data generation technique was developed. This method enhanced intent classification accuracy by 4.39% (from 75.86% to 80.25%) without compromising user privacy or requiring large-scale data collection from vulnerable populations. Using an optimized AR-based eye-gaze chatbot, this dissertation lays the foundation for novel eye-gaze-driven chatbot experiences. In addition, the synthetic data generation strategy for atypical linguistic patterns can help develop high-performance speech recognition, which is necessary for voice-based chatbot systems. These two types of chatbot systems can help close the digital divide for people with severe motor impairments. Future integration of synthetic data generation techniques into voice-based chatbots, in combination with the eye-gaze-based system, has the potential ii to further enhance accessibility and foster a more inclusive digital environment. This multimodal approach could afford the user choice between eye gaze and speech input, and thus better accommodate diverse motor and speech abilities.","abstract_html":"Ensuring equitable digital access for individuals with severe motor impairments remains a pressingchallenge. Conventional web navigation relies heavily on manual interactions—pointing, clicking, and typing—that are often inaccessible to users with limited motor function or atypical speech patterns. This research addresses the digital divide by proposing and evaluating two complementary solutions: (1) an eye gaze-controlled chatbot for hands-free, conversational access to online information, and (2) a synthetic data generation approach to improve voice-based chatbot systems’ ability to interpret atypical speech. First, an empirical study involving 20 participants established optimal parameters for eye-gaze target interaction in an Augmented Reality (AR) environment: a 2.25-meter eye-to-target distance and a 0.072-meter Area of Interest (Area of Interest (AOI)) diameter. These parameters achieved target selection rates exceeding 90%. Guided by these findings, the “EyeChat” system integrates an innovative circular text-entry interface that centralizes frequently used keys, reducing unnecessary eye movement. In a subsequent study with 12 participants, EyeChat demonstrated a 4.1-fold increase in text-entry speed (from 2.41 to 9.88 words per minute), a reduction in error rate (from 4.53% to 1.01%), and high user satisfaction, with over 83% of responses meeting or exceeding expectations. Second, to address the needs of individuals who rely on speech-based inputs yet exhibit atypical linguistic patterns, a novel synthetic data generation technique was developed. This method enhanced intent classification accuracy by 4.39% (from 75.86% to 80.25%) without compromising user privacy or requiring large-scale data collection from vulnerable populations. Using an optimized AR-based eye-gaze chatbot, this dissertation lays the foundation for novel eye-gaze-driven chatbot experiences. In addition, the synthetic data generation strategy for atypical linguistic patterns can help develop high-performance speech recognition, which is necessary for voice-based chatbot systems. These two types of chatbot systems can help close the digital divide for people with severe motor impairments. Future integration of synthetic data generation techniques into voice-based chatbots, in combination with the eye-gaze-based system, has the potential ii to further enhance accessibility and foster a more inclusive digital environment. This multimodal approach could afford the user choice between eye gaze and speech input, and thus better accommodate diverse motor and speech abilities.","abstract_has_math":false,"creators":["Mirbagheri, Mahya"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Biomedical Engineering","school":null,"contributors":[],"advisors":["Chau, Tom"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-06","date_published":"2025-06","updated_at":"2026-07-27T21:28:11Z","subjects":[],"languages":[],"rights":["Attribution-NonCommercial 4.0 International"],"rights_urls":["http://creativecommons.org/licenses/by-nc/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1807/144898","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Chau, Tom"]},{"key":"dc:contributor.department","label":"Department","values":["Biomedical Engineering"]},{"key":"dc:creator","label":"Author","values":["Mirbagheri, Mahya"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-06"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-30T15:53:33Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-30T15:53:33Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-06"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Attribution-NonCommercial 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://creativecommons.org/licenses/by-nc/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1807/144898"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Ensuring equitable digital access for individuals with severe motor impairments remains a pressingchallenge. Conventional web navigation relies heavily on manual interactions—pointing, clicking, and typing—that are often inaccessible to users with limited motor function or atypical speech patterns. This research addresses the digital divide by proposing and evaluating two complementary solutions: (1) an eye gaze-controlled chatbot for hands-free, conversational access to online information, and (2) a synthetic data generation approach to improve voice-based chatbot systems’ ability to interpret atypical speech. First, an empirical study involving 20 participants established optimal parameters for eye-gaze target interaction in an Augmented Reality (AR) environment: a 2.25-meter eye-to-target distance and a 0.072-meter Area of Interest (Area of Interest (AOI)) diameter. These parameters achieved target selection rates exceeding 90%. Guided by these findings, the “EyeChat” system integrates an innovative circular text-entry interface that centralizes frequently used keys, reducing unnecessary eye movement. In a subsequent study with 12 participants, EyeChat demonstrated a 4.1-fold increase in text-entry speed (from 2.41 to 9.88 words per minute), a reduction in error rate (from 4.53% to 1.01%), and high user satisfaction, with over 83% of responses meeting or exceeding expectations. Second, to address the needs of individuals who rely on speech-based inputs yet exhibit atypical linguistic patterns, a novel synthetic data generation technique was developed. This method enhanced intent classification accuracy by 4.39% (from 75.86% to 80.25%) without compromising user privacy or requiring large-scale data collection from vulnerable populations. Using an optimized AR-based eye-gaze chatbot, this dissertation lays the foundation for novel eye-gaze-driven chatbot experiences. In addition, the synthetic data generation strategy for atypical linguistic patterns can help develop high-performance speech recognition, which is necessary for voice-based chatbot systems. These two types of chatbot systems can help close the digital divide for people with severe motor impairments. Future integration of synthetic data generation techniques into voice-based chatbots, in combination with the eye-gaze-based system, has the potential ii to further enhance accessibility and foster a more inclusive digital environment. This multimodal approach could afford the user choice between eye gaze and speech input, and thus better accommodate diverse motor and speech abilities."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ed.D."]},{"key":"dc:title","label":"Title","values":["Design and Development of a Chatbot as an Alternative Web-browser for those with Severe Motor Impairments"]}]}],"canonical_facts":{"dc:contributor.advisor":["Chau, Tom"],"dc:contributor.department":["Biomedical Engineering"],"dc:creator":["Mirbagheri, Mahya"],"dc:date":["2025-06"],"dc:date.accessioned":["2025-07-30T15:53:33Z"],"dc:date.available":["2025-07-30T15:53:33Z"],"dc:date.issued":["2025-06"],"dc:description.abstract":["Ensuring equitable digital access for individuals with severe motor impairments remains a pressingchallenge. Conventional web navigation relies heavily on manual interactions—pointing, clicking, and typing—that are often inaccessible to users with limited motor function or atypical speech patterns. This research addresses the digital divide by proposing and evaluating two complementary solutions: (1) an eye gaze-controlled chatbot for hands-free, conversational access to online information, and (2) a synthetic data generation approach to improve voice-based chatbot systems’ ability to interpret atypical speech. First, an empirical study involving 20 participants established optimal parameters for eye-gaze target interaction in an Augmented Reality (AR) environment: a 2.25-meter eye-to-target distance and a 0.072-meter Area of Interest (Area of Interest (AOI)) diameter. These parameters achieved target selection rates exceeding 90%. Guided by these findings, the “EyeChat” system integrates an innovative circular text-entry interface that centralizes frequently used keys, reducing unnecessary eye movement. In a subsequent study with 12 participants, EyeChat demonstrated a 4.1-fold increase in text-entry speed (from 2.41 to 9.88 words per minute), a reduction in error rate (from 4.53% to 1.01%), and high user satisfaction, with over 83% of responses meeting or exceeding expectations. Second, to address the needs of individuals who rely on speech-based inputs yet exhibit atypical linguistic patterns, a novel synthetic data generation technique was developed. This method enhanced intent classification accuracy by 4.39% (from 75.86% to 80.25%) without compromising user privacy or requiring large-scale data collection from vulnerable populations. Using an optimized AR-based eye-gaze chatbot, this dissertation lays the foundation for novel eye-gaze-driven chatbot experiences. In addition, the synthetic data generation strategy for atypical linguistic patterns can help develop high-performance speech recognition, which is necessary for voice-based chatbot systems. These two types of chatbot systems can help close the digital divide for people with severe motor impairments. Future integration of synthetic data generation techniques into voice-based chatbots, in combination with the eye-gaze-based system, has the potential ii to further enhance accessibility and foster a more inclusive digital environment. This multimodal approach could afford the user choice between eye gaze and speech input, and thus better accommodate diverse motor and speech abilities."],"dc:description.degree":["Ed.D."],"dc:identifier.uri":["https://hdl.handle.net/1807/144898"],"dc:rights":["Attribution-NonCommercial 4.0 International"],"dc:rights.uri":["http://creativecommons.org/licenses/by-nc/4.0/"],"dc:title":["Design and Development of a Chatbot as an Alternative Web-browser for those with Severe Motor Impairments"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T21:28:11Z"}