Integrating social power into the decision-making of cognitive agents

Social norms-the unspoken commonsense rules about acceptable social behavior-are crucial in understanding the underlying causes and intents of people's actions in narratives. For example, underlying an action such as "wanting to call cops on my neighbor" are social norms that inform our conduct, such as "It is expected that you report crimes." We present SOCIAL CHEMISTRY, a new conceptual formalism to study people's everyday social norms and moral judgments over a rich spectrum of real life situations described in natural language. We introduce SOCIAL-CHEM-101, a large-scale corpus that catalogs 292k rules-of-thumb such as "It is rude to run a blender at 5am" as the basic conceptual units. Each rule-of-thumb is further broken down with 12 different dimensions of people's judgments, including social judgments of good and bad, moral foundations, expected cultural pressure, and assumed legality, which together amount to over 4.5 million annotations of categorical labels and free-text descriptions. Comprehensive empirical results based on state-of-the-art neural models demonstrate that computational modeling of social norms is a promising research direction. Our model framework, NEURAL NORM TRANSFORMER, learns and generalizes SOCIAL-CHEM-101 to successfully reason about previously unseen situations, generating relevant (and potentially novel) attribute-aware social rules-of-thumb. 1 Note that the social identities of the participants of situations would further inform which social norms are most

show abstract

“…for social norms could significantly hinder AI systems' ability to interact with humans (Pereira et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Social Chemistry 101: Learning to Reason about Social and Moral Norms

Forbes¹,

Hwang²,

Shwartz³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Although survey of the literature of social power shows many definitions of the concept; this does not suggest that all definitions are valid in all social contexts (Dowding, 2012). This is because power is a social construct that may be determined by clearly assigned and explicitly defined roles of a particular society (Pereira et al, 2016). This paper identifies three gaps in the study of social power.…”

Section: Introductionmentioning

confidence: 93%

“…Review of literature of power shows that the concept has different meanings (Pereira et al, 2016). Multiple meanings challenge the use of a single definition of power in different social contexts (Pansardi, 2012).…”

Section: Introductionmentioning

confidence: 99%

Perception of Concept and Practice of Social Power in Development Interventions in Malawi

Chimgonda-Nkhoma¹,

Garforth²,

Cardey³

et al. 2019

jae

View full text Add to dashboard Cite

show abstract

“…The effect of self-regulation can be explained from the third side -from the standpoint of the theory of systems, if we involve the system principle of non-equilibrium state in the analysis [20][21][22]. According to the latter, the system is in a dynamically non-equilibrium state if the equality between two oppositely directed forces of the system is violated:…”

Section: Analysis Of Dynamic Behavior Model Of the Mea From The Standmentioning

confidence: 99%

“…The obtained triad of theories that form the mathematical basis for describing the behavior of the MEA, is a reflection of the triad of approaches that form the basis of the concept of research and modeling of MES. The concept is based on the integration of approaches: system, dynamic (embodied in the theory of management), as well as cognitive and scenario, reflected in the economic theory [17,[19][20][21][22].…”

Section: Analysis Of Dynamic Behavior Model Of the Mea From The Standmentioning

confidence: 99%

Dynamic Model of Controlling the Behavior of an Economic Agent Using the Mechanism of Self-Regulation of Resource Flows

Ilyasov¹,

Макарова²,

Zakieva³

et al. 2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

The problem of development of the analytical system of simulation modeling (ASSM) of functioning processes of the economic system investigated at the macro level is considered. The structure of the complex of dynamic models of economic agents, which are considered at the macro level and presented in the form of firms, households (population), banks and the state, is presented. The concept of dynamic nonequilibrium mode of functioning of the macroeconomic system (MES) is introduced. The system principles for constructing dynamic models of behavior of macroeconomic agents (MEA) are stated. The dynamic model of the controlled behavior of the MEA which is analyzed from the standpoint of various approaches that demands performance of a number of transformations of the scheme of dynamic model is presented. The three variants of interpretation of the scheme of the dynamic model of the MEA behavior (from the standpoint of economic theory, control theory and systems theory) allowed to reveal the regularities of the MEA behavior in non-equilibrium modes. It is shown that non-equilibrium modes arising in the behavior of one agent extend to other agents. The proposed algorithm provides the restoration of the dynamic equilibrium mode of the whole MES. The application of controlled dynamic models of the MEA and the developed ASSM is advisable as a research system for the purpose of analyzing different management scenarios of the functioning process of the MES as a whole.

show abstract

Integrating social power into the decision-making of cognitive agents

Cited by 26 publications

References 29 publications

Social Chemistry 101: Learning to Reason about Social and Moral Norms

Social Chemistry 101: Learning to Reason about Social and Moral Norms

Perception of Concept and Practice of Social Power in Development Interventions in Malawi

Dynamic Model of Controlling the Behavior of an Economic Agent Using the Mechanism of Self-Regulation of Resource Flows

Contact Info

Product

Resources

About