Presentation on theme: "University of Liverpool"— Presentation transcript:
1 University of Liverpool A model for a motivational system grounded on value based abstract argumentation frameworksEugenio Di TullioFloriana GrassoUniversity of BariUniversity of LiverpoolItalyUK
2 The problem Digital interventions to promote healthy lifestyles More successful if grounded in robust behavioural theoryVariety of techniques to impact different stages of the planning processUse of different styles of interactionNew insights from recent research areas in AI:Persuasion technologyArgumentation Theory
3 Argument & Computation Over the last decade a core and autonomous discipline within AI, as opposed to permeating reasoning researchEmphasis on what persuades, not proofsHypothesis that the extent of acceptance is subjective, depending on the view of the audienceCrucial aspect within practical reasoning, as opposed to theoretical reasoningPresumptive schemataEmbraced by recent research in MultiAgent Systems
4 Application areas Multi-agent dialogue interactions Legal reasoning E.g. negotiation scenariosLegal reasoningE.g. tools to model and support case-based reasoningHealthcare adviceE.g. changing attitudes to healthy eatingMedical treatmentE.g. automated argument over organ transplantsFinanceE.g. automated stock market exchanges/contract
5 Directions of research Abstract argument systems: formal exploitation of simple notions of “attack” and “defense”.Logics for argumentation: formal models for automated reasoning.Dialogue protocols: emphasis on the rules that should govern the argumentation process and the participants to it.Argument schemes: stereotypical patterns for presumptive reasoning, fallacies.
6 Abstract Argumentation An argumentation framework (AF) is a pair F = (A, R) where A is a set of arguments R ⊆ A × A is a relation representing “attacks” or “defeats”. Different semantics to establish which arguments are “in” and which are “out”.
8 Motivational dialogues A subclass of argumentative dialoguesMain feature: a discussion around a behaviour, and the considerations of pros and cons of such behaviourCan’t be based on “facts” onlyHighly entrenched in the “value system” of the parties engaging in the discussionThere is no right or wrong answer – things change when perspectives change
9 ExampleA1: You should exercise twice a week because it improves your health.B2: Why is it good for my health?A3: Because exercise improves your stamina.B4: But then I might as well go to work by bike.A5: No, exercising is better for your health.B6: But exercise is boring.A7: What is more important: your health or having fun?B8: I find my health is more important. I guess I should exercise.(from van der Weide et al 2010 “Practical Reasoning Using Values”)
10 Practical Reasoning on Values and Perspectives Values: “desirable trans-situational goals, varying in importance, that serve as guiding principles in the life of a person or other social entity”Schwartz,S, Advances in experimental social psychology 25 (1992)Value Based Argumentation Framework (VAF)(Bench-Capon et al, Argumentation Research Group, University of Liverpool)Tuple <AR, attack, V, val, P>AR set of arguments; attacks relation on AR, V set of values, val function mapping from AR to V P set of possible audiences.An argument relates to value v if accepting it promotes or defends v.
11 Practical Reasoning on Values and Perspectives -ctd Values are discussed in terms of what condition promotes or demotes themE.g. treating people the same promotes the value of equality, exercising promotes the value of being healthyConditions and values can be promoted in degreesNot exercising is not healthy, exercising once a month is healthier, once a week is healthier stillPerspective: preorder on states representing a “topic” for discussion (e.g. health, fun)
12 Practical Reasoning on Values and Perspectives -ctd Perspectives can positively or negatively influence other perspectives forming chains(E.g. health positively influence wellbeing)When an agent has a “preference” over a perspective, this perspective becomes a “value”used as a “guiding principle” by the agentagent will try to reach as state maximally preferred from that perspective
13 ExampleHealth, Fun and Conformity perspectives are also valuesExercise perspective is not a value, but influences values(from van der Weide et al 2010 “Practical Reasoning Using Values”)
14 Motivational System Ultimate aim: Build an environment for digital interventions, based on motivational dialoguesAuthoring tools for creating user profiling, communication plans/strategies, styles of interactionMobile technology to acquire user’s preferences and lifestylesCentred around the notion of “Value System”
15 Prototype implementation A prototype built on top of Aspic (Argumentation Service Platform with Integrated Components - 6FP - Opensource)A platform to manage argumentation dialogues, which also provides services like reasoning, decision-making, learning.Concentrates on the managing of the value system and the practical reasoning on perspectivesLeft aside: user’s profiling and behavioural strategy implementation
18 Managing values Two value systems are maintained For the user and for “the system”Typical for dialogue systems representing “mutual” beliefsInteraction driven by a plan or “strategy” based on the user’s behavioural profiling (e.g. Transtheoretical model)E.g. topic of discussion based on the stage of changeSystem attempts to “utilise” user’s own beliefs and value system to maximise motivation impact
19 Example The system contains the states: Eating junk food less than 4 times a month;Eating junk food between 4 and 8 times a month;Eating junk food more than 8 times a monthAnd the perspectives to evaluate the states are Healthy eating; Fitness; Health; Social lifeInitial value systems are:
20 Evaluation of Transition A System attempts to make user “aware” of influences which could impact the evaluation of transition A
23 ConclusionsPreliminary work towards an argumentation based motivational systemAttempt to combine insights from argumentation theory and behavioural theoriesStill prototypical: need to include more reliable user model and full blown communication strategiesAdherence to standards (e.g. Aspic) looks beneficial in terms of cross-discipline evaluation