TS
T. Saveur
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
Contextualised Value Model
Designing a Robotic Model for Understanding the Context Dependency of Values for Enhanced Conversation Relevance
The promotion of desirable behaviours, such as socially appropriate or health-promoting actions, can be bolstered through a deeper understanding and awareness of the values that underpin the associated behavioural choices. Various implementations for promoting behaviour change based on goals already exist in Human-Robot Interaction, but, since values are the building blocks for our behaviour an agent can use values for behaviour change. By reflecting on value-related choices in a conversation, a conversational agent can assist in identifying the values at stake. This is particularly significant as these agents serve as accessible and non-judgemental platforms for discussing various concerns in a private setting. Such reflective conversations are time-consuming and may span multiple sessions, necessitating some form of memory (e.g., to reflect on earlier statements and compare the choices made for different situations).
While various robotic agents have been developed to provide behavioural support (e.g., for human health), the absence of a comprehensive memory structure and dialogue strategies capable of fostering personalised, reflective conversations based on the appreciation of certain values and actions in various scenarios through contextualised values remains a challenge. To address this, this study introduces the Contextualised Value Model – a dynamic memory model designed to facilitate value-based reflection and support personalised interactions between humans and robotic agents.
To realise this robotic memory, a conversational agent was designed that could elicit values from participants by discussing various scenarios that happen in daily life and reflecting on said values using perspective-taking and other dialogue strategies.
The evaluation of the Contextualised Value Model focused on three primary aspects: the model's accuracy, the influence on likeability and intelligence, and the effect on participants' value awareness. The model was evaluated during a between-subjects experiment (N=54), consisting of two conditions, one where the robot was able to update and use the Contextualised Value Model, and another one where the Contextualised Value Model was random throughout the conversation.
The outcome measures indicated that the integration of the memory model in conversations led to a personalised and relevant conversation, highlighting the potential of the Contextualised Value Model in enhancing conversation personalisation. Although participants' value awareness and perception of the robot's likeability and intelligence did not significantly differ based on the memory model, the study emphasised the need for extended observation to thoroughly evaluate long-term impacts.
Overall, the Contextualised Value Model presents a promising framework for enhancing personalised interactions in various real-world applications, emphasising the need for further research in this area. The ePartner4all project could be further developed to complement the efforts of primary school teachers and parents in supporting children's self-learning of socially, mentally, and physically desirable behaviours. ...
While various robotic agents have been developed to provide behavioural support (e.g., for human health), the absence of a comprehensive memory structure and dialogue strategies capable of fostering personalised, reflective conversations based on the appreciation of certain values and actions in various scenarios through contextualised values remains a challenge. To address this, this study introduces the Contextualised Value Model – a dynamic memory model designed to facilitate value-based reflection and support personalised interactions between humans and robotic agents.
To realise this robotic memory, a conversational agent was designed that could elicit values from participants by discussing various scenarios that happen in daily life and reflecting on said values using perspective-taking and other dialogue strategies.
The evaluation of the Contextualised Value Model focused on three primary aspects: the model's accuracy, the influence on likeability and intelligence, and the effect on participants' value awareness. The model was evaluated during a between-subjects experiment (N=54), consisting of two conditions, one where the robot was able to update and use the Contextualised Value Model, and another one where the Contextualised Value Model was random throughout the conversation.
The outcome measures indicated that the integration of the memory model in conversations led to a personalised and relevant conversation, highlighting the potential of the Contextualised Value Model in enhancing conversation personalisation. Although participants' value awareness and perception of the robot's likeability and intelligence did not significantly differ based on the memory model, the study emphasised the need for extended observation to thoroughly evaluate long-term impacts.
Overall, the Contextualised Value Model presents a promising framework for enhancing personalised interactions in various real-world applications, emphasising the need for further research in this area. The ePartner4all project could be further developed to complement the efforts of primary school teachers and parents in supporting children's self-learning of socially, mentally, and physically desirable behaviours. ...
The promotion of desirable behaviours, such as socially appropriate or health-promoting actions, can be bolstered through a deeper understanding and awareness of the values that underpin the associated behavioural choices. Various implementations for promoting behaviour change based on goals already exist in Human-Robot Interaction, but, since values are the building blocks for our behaviour an agent can use values for behaviour change. By reflecting on value-related choices in a conversation, a conversational agent can assist in identifying the values at stake. This is particularly significant as these agents serve as accessible and non-judgemental platforms for discussing various concerns in a private setting. Such reflective conversations are time-consuming and may span multiple sessions, necessitating some form of memory (e.g., to reflect on earlier statements and compare the choices made for different situations).
While various robotic agents have been developed to provide behavioural support (e.g., for human health), the absence of a comprehensive memory structure and dialogue strategies capable of fostering personalised, reflective conversations based on the appreciation of certain values and actions in various scenarios through contextualised values remains a challenge. To address this, this study introduces the Contextualised Value Model – a dynamic memory model designed to facilitate value-based reflection and support personalised interactions between humans and robotic agents.
To realise this robotic memory, a conversational agent was designed that could elicit values from participants by discussing various scenarios that happen in daily life and reflecting on said values using perspective-taking and other dialogue strategies.
The evaluation of the Contextualised Value Model focused on three primary aspects: the model's accuracy, the influence on likeability and intelligence, and the effect on participants' value awareness. The model was evaluated during a between-subjects experiment (N=54), consisting of two conditions, one where the robot was able to update and use the Contextualised Value Model, and another one where the Contextualised Value Model was random throughout the conversation.
The outcome measures indicated that the integration of the memory model in conversations led to a personalised and relevant conversation, highlighting the potential of the Contextualised Value Model in enhancing conversation personalisation. Although participants' value awareness and perception of the robot's likeability and intelligence did not significantly differ based on the memory model, the study emphasised the need for extended observation to thoroughly evaluate long-term impacts.
Overall, the Contextualised Value Model presents a promising framework for enhancing personalised interactions in various real-world applications, emphasising the need for further research in this area. The ePartner4all project could be further developed to complement the efforts of primary school teachers and parents in supporting children's self-learning of socially, mentally, and physically desirable behaviours.
While various robotic agents have been developed to provide behavioural support (e.g., for human health), the absence of a comprehensive memory structure and dialogue strategies capable of fostering personalised, reflective conversations based on the appreciation of certain values and actions in various scenarios through contextualised values remains a challenge. To address this, this study introduces the Contextualised Value Model – a dynamic memory model designed to facilitate value-based reflection and support personalised interactions between humans and robotic agents.
To realise this robotic memory, a conversational agent was designed that could elicit values from participants by discussing various scenarios that happen in daily life and reflecting on said values using perspective-taking and other dialogue strategies.
The evaluation of the Contextualised Value Model focused on three primary aspects: the model's accuracy, the influence on likeability and intelligence, and the effect on participants' value awareness. The model was evaluated during a between-subjects experiment (N=54), consisting of two conditions, one where the robot was able to update and use the Contextualised Value Model, and another one where the Contextualised Value Model was random throughout the conversation.
The outcome measures indicated that the integration of the memory model in conversations led to a personalised and relevant conversation, highlighting the potential of the Contextualised Value Model in enhancing conversation personalisation. Although participants' value awareness and perception of the robot's likeability and intelligence did not significantly differ based on the memory model, the study emphasised the need for extended observation to thoroughly evaluate long-term impacts.
Overall, the Contextualised Value Model presents a promising framework for enhancing personalised interactions in various real-world applications, emphasising the need for further research in this area. The ePartner4all project could be further developed to complement the efforts of primary school teachers and parents in supporting children's self-learning of socially, mentally, and physically desirable behaviours.
Bachelor thesis
(2020)
-
R.F. Huisman, S. Weegink, S.B.M. Kaptein, A.J. Jeleniewski, T. Saveur, S. Picek, Christian Doerr, O.W. Visser
The internet consists of many networks connected by the BGP protocol and can easily be manipulated by a hacker. Every day, hackers reroute internet traffic and use that to impersonate entities such as companies, devices and humans. To detect this rerouting, which is also know as a route leak, a BGP monitor can be used. A BGP monitor checks whether the local route is correct by comparing the local route to the route from hundreds of devices. The lower the percentage of the routes that are the same, the bigger the chance there is a route leak. Hence, a user can tell whether a hacker manipulated the route. This project aims to build a BGP monitor application, that will ease the process of finding whether a hacker rerouted a part of the internet. To achieve this, the Internet Monitor application has been developed. In the Internet Monitor, an admin can add different types of tasks that will be run by the devices. This input will then be transmitted to the backend and to the database, where they will be stored. After some time, the backend will send out the tasks to the nodes. The nodes will execute the task and send back the results to the backend. These results can then be used to check whether the information from BGP servers or the local result is the same, and thus not manipulated. Apart from this, Internet Monitor also offers the possibility to see the map of all the real-time traffic between devices.
...
The internet consists of many networks connected by the BGP protocol and can easily be manipulated by a hacker. Every day, hackers reroute internet traffic and use that to impersonate entities such as companies, devices and humans. To detect this rerouting, which is also know as a route leak, a BGP monitor can be used. A BGP monitor checks whether the local route is correct by comparing the local route to the route from hundreds of devices. The lower the percentage of the routes that are the same, the bigger the chance there is a route leak. Hence, a user can tell whether a hacker manipulated the route. This project aims to build a BGP monitor application, that will ease the process of finding whether a hacker rerouted a part of the internet. To achieve this, the Internet Monitor application has been developed. In the Internet Monitor, an admin can add different types of tasks that will be run by the devices. This input will then be transmitted to the backend and to the database, where they will be stored. After some time, the backend will send out the tasks to the nodes. The nodes will execute the task and send back the results to the backend. These results can then be used to check whether the information from BGP servers or the local result is the same, and thus not manipulated. Apart from this, Internet Monitor also offers the possibility to see the map of all the real-time traffic between devices.