Social Machines for All

Petros Papapanagiotou, Alan Davoust, Dave Murray-Rust, Areti Manataki, Max Van Kleek, Nigel Shadbolt, Dave Robertson

Abstract: In today's interconnected world, people interact to a unprecedented degree through the use of digital platforms and services, forming complex 'social machines'. These are now homes to autonomous agents as well as people, providing an open space where human and computational intelligence can mingle---a new frontier for distributed agent systems. However, participants typically have limited autonomy to define and shape the machines they are part of. In this paper, we envision a future where individuals are able to develop their own Social Machines, enabling them to interact in a trustworthy, decentralized way. To make this possible, development methods and tools must see their barriers-to-entry dramatically lowered. People should be able to specify the agent roles and interaction patterns in an intuitive, visual way, analyse and test their designs and deploy them as easy to use systems. We argue that this is a challenging but realistic goal, which should be tackled by navigating the trade-off between the accessibility of the design methods --primarily the modelling formalisms-- and their expressive power. We support our arguments by drawing ideas from different research areas including electronic institutions, agent-based simulation, process modelling, formal verification, and model-driven engineering.

External IDs:dblp:conf/atal/PapapanagiotouD18