umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Semantic model for adaptive human-agent dialogues
Umeå University, Faculty of Science and Technology, Department of Computing Science.
Umeå University, Faculty of Science and Technology, Department of Computing Science.
2014 (English)Manuscript (preprint) (Other academic)
Abstract [en]

A common conversation between an older adult and a nurse about health-related issues includes topics such as troubles with sleep, reasons for walking around nighttime, pain conditions, etc. Such a dialogue can be regarded as a "natural" dialogue emerging from the participating agents' lines of thinking, their roles, needs and motives, while switching between topics as the dialogue unfolds. The purpose of this work is to define a generic model of purposeful human-agent dialogues suitable for health-related topics. This is done based on analyses of scenarios, personas and models of human behavior. The results include four models, which need to be included in a software agent's belief base; i) a user model, ii) a model of the domain knowledge related to the topic of the dialogue, iii) an agent model, and iv) a dialogue activity model. The models were implemented into a prototype system for human-agent dialogues, which was evaluated by therapists and a group of older adults.

Place, publisher, year, edition, pages
2014.
Keyword [en]
personalization, dialogue systems, health promotion, argumentation, intelligent agent, user model
National Category
Computer Science
Identifiers
URN: urn:nbn:se:umu:diva-96755OAI: oai:DiVA.org:umu-96755DiVA: diva2:767610
Available from: 2014-12-02 Created: 2014-12-02 Last updated: 2015-05-11Bibliographically approved
In thesis
1. Adaptive human-agent dialogues for reasoning about health
Open this publication in new window or tab >>Adaptive human-agent dialogues for reasoning about health
2014 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

The aim of this research is to develop new theories, methods and technology, which enables adaptive and personalised dialogues between a human and a software agent, to handle everyday queries about health that are perceived as meaningful and useful to the human. Some of the challenges to build such human-agent dialogue system are the following. The agent needs to have knowledge about the human, the topic of the dialogue, the knowledge domain of the topic, and also about the physical and social environment. Moreover, the agent must know about itself, its role, purpose and limitations. It must know how to be cooperative and be able to behave and express with empathy while conducting a dialogue activity. In some situations, it needs to reason and make decisions about a topic together with the human and about its own behavior. To be able to do this, it needs the capability to evaluate its behavior in the context in which the dialogue takes place. These challenges are addressed by developing formal semantic models to provide the agent with tools to build their knowledge and to be able to reason and make decisions. These models were developed based on literature studies, theories of human activity, argumentation theory, personas and scenarios.

The models were formalised and implemented using Semantic Web technology, and integrated into a human-agent dialogue system. The system was evaluated with a group of therapists and a group of elderly people, who showed curiosity and interest in having dialogues with a software agent on various topics.

The formal models that the agent constructs are adapted to the specific situation and to the human actor participating in a dialogue. They are based on four models: a model with knowledge about the human actor, a model of itself, a domain model, and a dialogue activity model. The dialogue activity is based on argumentation schemes, which function as patterns of reasoning and for the dialogue execution. These models allow the agent and the human actor to conduct flexible and nested sub-dialogues with different purposes within a main dialogue about a topic. The agent can adapt its moves to the human actor's trail of reasoning, to the human's priorities and goals, and to some human's emotional state. A method for the agent to be able to evaluate its behavior was also developed and evaluated. The proportion of appropriate moves in relation to the local context of earlier moves in the dialogue was 90% in the pilot study, which indicates that the agent's strategies for selecting moves can be improved.

Future research will focus on further development of reasoning methods, learning and assessment methods, and interface design. The results will be applied to additional knowledge domains to test its domain independence and will be evaluated with different groups of potential users.

Place, publisher, year, edition, pages
Umeå: Umeå universitet, 2014. 32 p.
Series
Report / UMINF, ISSN 0348-0542 ; 14.19
National Category
Computer Science
Identifiers
urn:nbn:se:umu:diva-96756 (URN)978-91-7601-135-5 (ISBN)
Supervisors
Available from: 2014-12-02 Created: 2014-12-02 Last updated: 2014-12-02Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Baskar, JayalakshmiLindgren, Helena
By organisation
Department of Computing Science
Computer Science

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 200 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf