Simuler la diffusion d’une innovation agricole à l’aide de modèles à base d’agents et de l’argumentation formelle
Revue Ouverte d'Intelligence Artificielle, Volume 2 (2021) no. 1, pp. 65-93.

L’agriculture constitue aujourd’hui l’un des principaux utilisateurs de la ressource en eau. Dans ce contexte, de nombreux travaux ont mis en avant l’intérêt des compteurs communicants pour mieux gérer cette ressource. Néanmoins, ces compteurs posent des questions en termes d’acceptabilité, ce qui nuit à la diffusion de ces technologies auprès des agriculteurs. Nous proposons donc de recourir à la simulation à base d’agents pour mieux comprendre les dynamiques et les freins à leur diffusion. Contrairement à la grande majorité des travaux sur la diffusion d’innovations qui se limitent à une représentation abstraite et simplifiée de ce processus, nous proposons dans cet article un modèle générique reposant sur la théorie du comportement planifié et sur l’argumentation formelle permettant d’expliquer les raisons du changement d’opinion d’un agent, élément fondamental pour comprendre la dynamique de diffusion de l’innovation. Chaque agent a ainsi la possibilité d’échanger des arguments avec un autre et de construire son opinion sur une innovation à partir de l’ensemble des arguments qu’il connaît. Les premières expérimentations menées à partir de données recueillies auprès des agriculteurs de la rivière du Louts montrent une tendance à une plus grande adoption de ces compteurs et soulignent l’importance que peuvent avoir les fake news ainsi que certains arguments critiques sur le processus d’adoption.

Agriculture is one of the main users of water resources today. In this context, many studies have highlighted the interest of communicating meters to better manage this resource. Nevertheless, these meters raise questions in terms of acceptability, which hinders the diffusion of these technologies to farmers. We therefore propose to use agent-based simulation to better understand the dynamics and obstacles to their diffusion. Contrary to the vast majority of works on the diffusion of innovations, which are limited to an abstract and simplified representation of this process, we propose in this article a generic model based on the theory of planned behavior, and on formal argumentation in order to explain the reasons for the change of opinion of an agent, which is a fundamental element to understand the dynamics of diffusion of innovation. Each agent has thus the possibility to exchange arguments with another agent and to build his/her opinion on an innovation from the set of arguments he/she knows. The first experiments carried out with data collected from farmers of the Louts river show a tendency towards a greater adoption of these meters, as well as the importance that fake news and certain critical arguments can have on the adoption process.

Reçu le :
Révisé le :
Accepté le :
Publié le :
DOI : 10.5802/roia.10
Mot clés : Simulation à base d’agents, diffusion d’innovation, argumentation, théorie du comportement planifié.
Keywords: Agent-based simulation, Diffusion of innovation, Argumentation, Theory of planned ehaviour

Loïc Sadou 1 ; Stéphane Couture 1 ; Rallou Thomopoulos 2 ; Patrick Taillandier 3, 1, 4

1 Université de Toulouse, INRAE, UR MIAT, F-31320, Castanet-Tolosan, France
2 IATE, Univ Montpellier, INRAE, Institut Agro, Montpellier, France
3 UMI UMMISCO, IRD, France
4 WARM Team, Thuyloi University, Vietnam
Licence : CC-BY 4.0
Droits d'auteur : Les auteurs conservent leurs droits
@article{ROIA_2021__2_1_65_0,
     author = {Lo{\"\i}c Sadou and St\'ephane Couture and Rallou Thomopoulos and Patrick Taillandier},
     title = {Simuler la diffusion d{\textquoteright}une innovation agricole \`a l{\textquoteright}aide de mod\`eles \`a base d{\textquoteright}agents et de l{\textquoteright}argumentation formelle},
     journal = {Revue Ouverte d'Intelligence Artificielle},
     pages = {65--93},
     publisher = {Association pour la diffusion de la recherche francophone en intelligence artificielle},
     volume = {2},
     number = {1},
     year = {2021},
     doi = {10.5802/roia.10},
     language = {fr},
     url = {https://roia.centre-mersenne.org/articles/10.5802/roia.10/}
}
TY  - JOUR
AU  - Loïc Sadou
AU  - Stéphane Couture
AU  - Rallou Thomopoulos
AU  - Patrick Taillandier
TI  - Simuler la diffusion d’une innovation agricole à l’aide de modèles à base d’agents et de l’argumentation formelle
JO  - Revue Ouverte d'Intelligence Artificielle
PY  - 2021
SP  - 65
EP  - 93
VL  - 2
IS  - 1
PB  - Association pour la diffusion de la recherche francophone en intelligence artificielle
UR  - https://roia.centre-mersenne.org/articles/10.5802/roia.10/
DO  - 10.5802/roia.10
LA  - fr
ID  - ROIA_2021__2_1_65_0
ER  - 
%0 Journal Article
%A Loïc Sadou
%A Stéphane Couture
%A Rallou Thomopoulos
%A Patrick Taillandier
%T Simuler la diffusion d’une innovation agricole à l’aide de modèles à base d’agents et de l’argumentation formelle
%J Revue Ouverte d'Intelligence Artificielle
%D 2021
%P 65-93
%V 2
%N 1
%I Association pour la diffusion de la recherche francophone en intelligence artificielle
%U https://roia.centre-mersenne.org/articles/10.5802/roia.10/
%R 10.5802/roia.10
%G fr
%F ROIA_2021__2_1_65_0
Loïc Sadou; Stéphane Couture; Rallou Thomopoulos; Patrick Taillandier. Simuler la diffusion d’une innovation agricole à l’aide de modèles à base d’agents et de l’argumentation formelle. Revue Ouverte d'Intelligence Artificielle, Volume 2 (2021) no. 1, pp. 65-93. doi : 10.5802/roia.10. https://roia.centre-mersenne.org/articles/10.5802/roia.10/

[1] Icek Ajzen The theory of planned behavior, Organizational behavior and human decision processes, Volume 50 (1991) no. 2, pp. 179-211 | DOI

[2] Leila Amgoud; Jonathan Ben-Naim; Dragan Doder; Srdjan Vesic Acceptability Semantics for Weighted Argumentation Frameworks, Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (2017), pp. 56-62 https://www.ijcai.org/proceedings/2017/9 | DOI

[3] Sven Banisch; Eckehard Olbrich An Argument Communication Model of Polarization and Ideological Alignment, Journal of Artificial Societies and Social Simulation, Volume 24 (2021) no. 1, 1, 22 pages http://jasss.soc.surrey.ac.uk/24/1/1.html | DOI

[4] Frank M. Bass A New Product Growth for Model Consumer Durables, Management Science, Volume 15 (1969) no. 5, pp. 215-227 | DOI

[5] Philippe Besnard; Anthony Hunter Elements of Argumentation, The MIT Press, 2008

[6] Philippe Besnard; Anthony Hunter Elements of Argumentation, The MIT Press, 2008

[7] João Augusto Rossi Borges; Alfons G.J.M. Oude Lansink; Claudio Marques Ribeiro; Vanessa Lutke Understanding farmers’ intention to adopt improved natural grassland using the theory of planned behavior, Livestock Science, Volume 169 (2014), pp. 163-174 https://linkinghub.elsevier.com/retrieve/pii/S1871141314004818 | DOI

[8] Jean-Rémi Bourguet; Rallou Thomopoulos; Marie-Laure Mugnier; Joël Abécassis An Artificial Intelligence-Based Approach to Deal with Argumentation Applied to Food Quality in a Public Health Policy, Expert Systems with Applications, Volume 40 (2013) no. 11, pp. 4539-4546 | DOI

[9] Jean-Rémi Bourguet; Rallou Thomopoulos; Marie-Laure Mugnier; Joël Abécassis An artificial intelligence-based approach to deal with argumentation applied to food quality in a public health policy, Expert Systems with Applications, Volume 40 (2013) no. 11, pp. 4539-4546 | DOI

[10] George Butler; Gabriella Pigozzi; Juliette Rouchier Mixing Dyadic and Deliberative Opinion Dynamics in an Agent-Based Model of Group Decision-Making, Complexity, Volume 2019 (2019), 3758159, 32 pages | DOI

[11] George Butler; Gabriella Pigozzi; Juliette Rouchier An Opinion Diffusion Model with Vigilant Agents and Deliberation, International Workshop on Multi-Agent Systems and Agent-Based Simulation (2019), pp. 81-99

[12] Álvaro Carrera; Carlos A. Iglesias A systematic review of argumentation techniques for multi-agent systems research, Artificial Intelligence Review, Volume 44 (2015) no. 4, pp. 509-535 http://link.springer.com/10.1007/s10462-015-9435-9 | DOI

[13] Guillaume Deffuant Improving agri-environmental policies : a simulation apporoach to the cognitive properties of farmers and institutions, 2001

[14] Guillaume Deffuant; Sylvie Huet; Frédéric Amblard An individual-based model of innovation diffusion mixing social value and individual benefit, American Journal of Sociology, Volume 110 (2005) no. 4, pp. 1041-1069 | DOI

[15] Guillaume Deffuant; David Neau; Frederic Amblard; Gérard Weisbuch Mixing beliefs among interacting agents, Advances in Complex Systems, Volume 3 (2000) no. 01n04, pp. 87-98 | DOI

[16] P. M. Dung On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games, Artificial Intelligence Journal, Volume 77 (1995) no. 2, pp. 321-357 | DOI

[17] Joan-Maria Esteban; Debraj Ray On the measurement of polarization, Econometrica : Journal of the Econometric Society, Volume 62 (1994) no. 4, pp. 819-851 | DOI

[18] Simone Gabbriellini; Paolo Torroni MS Dialogues : Persuading and getting persuaded, e74516 (22 pages)

[19] Simone Gabbriellini; Paolo Torroni A new framework for ABMs based on argumentative reasoning, Advances in Social Simulation, Springer, 2014, pp. 25-36 | DOI

[20] Patrice Garin; Marielle Montginoul; Laure Collard La télé-relève pour la gestion de l’eau d’irrigation : Contraintes & potentialités (2019) (Technical report)

[21] Peter Kaufmann; Sigrid Stagl; Daniel W. Franks Simulating the diffusion of organic farming practices in two New EU Member States, Ecological Economics, Volume 68 (2009) no. 10, pp. 2580-2593 https://linkinghub.elsevier.com/retrieve/pii/S0921800909001372 | DOI

[22] Michael Mäs; Andreas Flache Differentiation without distancing. Explaining bi-polarization of opinions without negative influence, PloS one, Volume 8 (2013) no. 11, e74516

[23] Hugo Mercier; Dan Sperber Why do humans reason ? Arguments for an argumentative theory, Behavioral and Brain Sciences, Volume 34 (2011) no. 2, pp. 57-74 https://www.cambridge.org/core/product/identifier/S0140525X10000968/type/journal_article | DOI

[24] Marielle Montginoul; P. Garin; K. Abannar; D. Lepercq Le compteur communicant : perception des irrigants : Le cas du bassin du Louts, Techniques Sciences Méthodes (2019), pp. 39-47 | DOI

[25] Iyad Rahwan; Sarvapali D. Ramchurn; Nicholas R. Jennings; Peter McBURNEY; Simon Parsons; Liz Sonenberg Argumentation-based negotiation, The Knowledge Engineering Review, Volume 18 (2003) no. 4, pp. 343-375 https://www.cambridge.org/core/product/identifier/S0269888904000098/type/journal_article | DOI

[26] Everett M. Rogers Diffusion of innovations, Free Press, New York, NY [u.a.], 1962, 576 pages

[27] Thomas Saaty; Mujgan Sagir Ozdemir Why the magic number seven plus or minus two, Mathematical and Computer Modelling, Volume 38 (2003) no. 3-4, pp. 233-244 | DOI

[28] Annalisa Stefanelli; Roman Seidl Moderate and polarized opinions. Using empirical data for an agent-based simulation, Social Simulation Conference (2014), 3

[29] Annalisa Stefanelli; Roman Seidl Opinion communication on contested topics : How empirics and arguments can improve social simulation, Journal of Artificial Societies and Social Simulation, Volume 20 (2017) no. 4, 3, 19 pages | DOI

[30] Patrick Taillandier; Benoit Gaudou; Arnaud Grignard; Quang-Nghi Huynh; Nicolas Marilleau; Philippe Caillou; Damien Philippon; Alexis Drogoul Building, composing and experimenting complex spatial models with the GAMA platform, GeoInformatica, Volume 23 (2019) no. 2, pp. 299-322 | DOI

[31] Patrick Taillandier; Nicolas Salliou; Rallou Thomopoulos Coupling agent-based models and argumentation framework to simulate opinion dynamics : application to vegetarian diet diffusion, Social Simulation Conference 2019 (2019)

[32] Patrick Taillandier; Nicolas Salliou; Rallou Thomopoulos Introducing the Argumentation Framework Within Agent-Based Models to Better Simulate Agents’ Cognition in Opinion Dynamics : Application to Vegetarian Diet Diffusion, Journal of Artificial Societies and Social Simulation, Volume 24 (2021) no. 2, 6, 29 pages http://jasss.soc.surrey.ac.uk/24/2/6.html | DOI

[33] Nouredine Tamani; Patricio Mosse; Madalina Croitoru; Patrice Buche; Valérie Guillard; Carole Guillaume; Nathalie Gontard An Argumentation System for Eco-Efficient Packaging Material Selection, Computers and Electronics in Agriculture, Volume 113 (2015), 3758159, pp. 174-192 | DOI

[34] Rallou Thomopoulos A practical application approach to argumentation for multicriteria analysis and decision support, EURO Journal on Decision Processes, Volume 6 (2018), pp. 237-255 | DOI

[35] Rallou Thomopoulos; Madalina Croitoru; Nouredine Tamani Decision support for agri-food chains : A reverse engineering argumentation-based approach, Ecological Informatics, Volume 26 (2015) no. 2, pp. 182-191 | DOI

[36] Rallou Thomopoulos; Bernard Moulin; Laurent Bedoussac Supporting decision for environment-friendly practices in the agri-food sector, International Journal of Agricultural and Environmental Information Systems, Volume 9 (2018) no. 3, pp. 1-21 | DOI

[37] Rallou Thomopoulos; Nicolas Salliou; Carolina Abreu; Vincent Cohen; Timothée Fouqueray Reduced meat consumption : from multicriteria argument modelling to agent-based social simulation, International Journal of Food Studies, Volume 10 (2021) no. 1, pp. 133-149 | DOI

[38] Ingo Wolf; Tobias Schröder; Jochen Neumann; Gerhard de Haan Changing minds about electric cars : An empirically grounded agent-based modeling approach, Technological forecasting and social change, Volume 94 (2015), pp. 269-285 | DOI

[39] Masoud Yazdanpanah; Dariush Hayati; Stefan Hochrainer-Stigler; Gholam Hosein Zamani Understanding farmers’ intention and behavior regarding water conservation in the Middle-East and North Africa : A case study in Iran, Journal of Environmental Management, Volume 135 (2014), 1, pp. 63-72 | DOI

[40] Bruno Yun; Rallou Thomopoulos; Pierre Bisquert; Madalina Croitoru Defining Argumentation Attacks in Practice : An Experiment in Food Packaging Consumer Expectations, Graph-Based Representation and Reasoning (2018), pp. 73-87 | DOI

[41] Haifeng Zhang; Yevgeniy Vorobeychik Empirically grounded agent-based models of innovation diffusion : a critical review, Artificial Intelligence Review, Volume 52 (2019), 6, pp. 707-741 | DOI

Cité par Sources :