Recognizing Intentions from Rejoinders in a Bayesian Interactive Argumentation System

Zukerman, Ingrid; Jitnah, Nathalie; McConachy, Richard; George, Sarah

doi:10.1007/3-540-44533-1_28

Cited by 12 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering probability theory and belief networks as a method for treating uncertainty is not a novelty in the argumentation community. BIAS was the first such system [14]. Gratton [15] proposed to measure the strength of support in probabilistic terms.…”

Section: Discussionmentioning

confidence: 99%

Persuasion Artifices to Promote Wellbeing

Rosis

Mazzotta

Miceli

et al. 2006

Persuasive Technology

View full text Add to dashboard Cite

We propose a theory of a-rational persuasion in which we integrate emotional and non emotional strategies by arguing that they both imply reasoning and planning abilities in the two participants. We show some examples of texts from a corpus of persuasion messages in the healthy eating domain and propose a formalism to represent this knowledge. The final goal of our research is to simulate user-adapted persuasion dialogs about healthy eating.

show abstract

Section: Discussionmentioning

confidence: 99%

Persuasion Artifices to Promote Wellbeing

Rosis

Mazzotta

Miceli

et al. 2006

Persuasive Technology

View full text Add to dashboard Cite

show abstract

“…9 The measure of impact in (Zukerman, 2000), considers the same elements, although with a function of different shape (logarithm of the ratio between posterior and prior probability).…”

Section: Measuring Impactmentioning

confidence: 99%

“…Definition 5. We say that: IM-S-R is probabilistically compatible with OWN-S if its parameters are defined so that the weights of the links among the nodes that the two models share are the same (the conditional probability tables are marginalized as in Zukerman et al 2000).…”

Section: Building a Image Of The Receiver's Mental Statementioning

confidence: 99%

“…• if p j = (Phys-abil = "is agile"), Imp 1 (p j ← p i ) = 0.47 and Imp 2 (p j ← p i ) = 0.81 • if p j = (Phys-abil = "can lift heavy weights"), Imp 1 (p j ← p i ) = 0.74 and Imp 2 (p j ← p i ) = 0.92 The second alternative ("X can lift heavy weights") is preferable. 9 The measure of impact in (Zukerman, 2000), considers the same elements, although with a function of different shape (logarithm of the ratio between posterior and prior probability).…”

Section: Measuring Impactmentioning

confidence: 99%

“…In Human-Computer interaction (HCI) and multi-agent systems (MAS), users and agents are presumed to always say the truth: the sincerity assertion is a baseline assumption in the great majority of dialog systems (see, for instance, Carberry and Lambert 1999;Paek and Horvitz 2000;Zukerman et al 2000). This hypothesis is usually justified by claiming that HCI and MAS are based on the principle of cooperation and that cooperation would imply sincerity in all performances.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Can Computers Deliberately Deceive? A Simulation Tool and Its Application to Turing's Imitation Game

Rosis

Carofiglio

Grassano

et al. 2003

Computational Intelligence

View full text Add to dashboard Cite

In this paper, we describe how agents can deceive within a probabilistic framework for representing their mental state: in doing so, we challenge the so-called sincerity assumption in Human-Computer interaction (HCI) and multi-agent systems (MAS). We distinguish deception from its special case of lie and characterize different forms of deception, by identifying several criteria for distinguishing among them. In particular, we propose a model of information impact on the Receiver's mind. As the message Sender must plan its strategy by considering the Receiver's criteria for believing, we also discuss some of these criteria, like content plausibility, source informativity, and information safety. We apply this model to a simplified version of Turing's Imitation Game and describe how we implemented a Simulator of deceptive strategies that we called Mouth of Truth. We conclude the paper by describing an evaluation study that enabled us to verify the validity of our method and to revise it in part.

show abstract