Grant: Discovery Grants Program - Individual
University of Toronto
$36,000.00
User Communication with Artificial Agents through Conversational Interfaces
EF 2024-25
Résumé
The growing complexity of intelligent systems and their active decoupling from direct user input create a promising environment for the shift in a user experience paradigm: from pure human-system interaction to human-system communication and collaboration. This is further amplified by the increased popularity of entity-based system interfaces (artificial agents, e.g. Siri, Google Assistant, Alexa, etc.). The success of human collaboration with AI systems that make use of artificial agents is predicated upon the ability of humans and AI to effectively communicate, which involves the ability to understand each other and to efficiently present the information to each other. To ease these communication processes, system developers actively integrate rapidly developing conversational user interfaces (CUI), which simulate natural human conversation. CUI is known to trigger the user's tendency for anthropomorphization of the systems, forming the basis for user expectations and predispositions regarding agents' behaviour, reliability, interaction dynamics, etc. While there is early evidence that the specifics of anthropomorphized perceptions of agents are affected by the structure and the flow of their conversation, i.e. the architecture of the agent's conversation, however, currently, our understanding of conversation architecture requirements for CUI-enabled agents is virtually absent.
In this research program, I will implement effective conversation-based communication between users and AI CUI-enabled agents through developing knowledge on how the conversation architecture (1) affects users' anthropomorphized perceptions of these agents, (2) affects users' interpretation of the information provided by these agents, and (3) how we can dynamically support adaptations of conversation architectures to communication contexts. Correspondingly, the program objectives are structured around two major research questions: What synthesis characteristics of the agent's conversation architecture affect users' perceptions of CUI-empowered agents (e.g. intelligence, professionalism, personality, approachability)? What structural and format characteristics of output in CUI-based information presentation affect information interpretation (e.g. information trustworthiness, reliability, relevance) in human-agent collaborative decision-making processes? The proposed program involves training of 12 HQPs (2 Ph.D. students and 10 masters' students). This research is anticipated to directly impact product development through informing design and implementation of intelligent agent conversation. The results will inform the algorithmic structure of the process, approaches to intent recognition and response synthesis, and appropriate system feedback. The impact is expected through academic publications, industry collaborations, incorporation of the results in professional teaching programs, and dissemination of the results to the broader audience to increase public visibility.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2023-05053
Name nom
Kuzminykh, Anastasia
Department département
Faculty of Information
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
36000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2710
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information systems design
Research subject fr
Conception de systèmes d'information
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
User Communication with Artificial Agents through Conversational Interfaces
Keywords
conversational interfaces; conversational agents; human-agent collaboration; intelligent agents; intelligent personal assistants; ubiquitous systems; anthropomorphism
Application summary
The growing complexity of intelligent systems and their active decoupling from direct user input create a promising environment for the shift in a user experience paradigm: from pure human-system interaction to human-system communication and collaboration. This is further amplified by the increased popularity of entity-based system interfaces (artificial agents, e.g. Siri, Google Assistant, Alexa, etc.). The success of human collaboration with AI systems that make use of artificial agents is predicated upon the ability of humans and AI to effectively communicate, which involves the ability to understand each other and to efficiently present the information to each other. To ease these communication processes, system developers actively integrate rapidly developing conversational user interfaces (CUI), which simulate natural human conversation. CUI is known to trigger the user's tendency for anthropomorphization of the systems, forming the basis for user expectations and predispositions regarding agents' behaviour, reliability, interaction dynamics, etc. While there is early evidence that the specifics of anthropomorphized perceptions of agents are affected by the structure and the flow of their conversation, i.e. the architecture of the agent's conversation, however, currently, our understanding of conversation architecture requirements for CUI-enabled agents is virtually absent.
In this research program, I will implement effective conversation-based communication between users and AI CUI-enabled agents through developing knowledge on how the conversation architecture (1) affects users' anthropomorphized perceptions of these agents, (2) affects users' interpretation of the information provided by these agents, and (3) how we can dynamically support adaptations of conversation architectures to communication contexts. Correspondingly, the program objectives are structured around two major research questions: What synthesis characteristics of the agent's conversation architecture affect users' perceptions of CUI-empowered agents (e.g. intelligence, professionalism, personality, approachability)? What structural and format characteristics of output in CUI-based information presentation affect information interpretation (e.g. information trustworthiness, reliability, relevance) in human-agent collaborative decision-making processes? The proposed program involves training of 12 HQPs (2 Ph.D. students and 10 masters' students). This research is anticipated to directly impact product development through informing design and implementation of intelligent agent conversation. The results will inform the algorithmic structure of the process, approaches to intent recognition and response synthesis, and appropriate system feedback. The impact is expected through academic publications, industry collaborations, incorporation of the results in professional teaching programs, and dissemination of the results to the broader audience to increase public visibility.