[Paper Review] Understanding the Social Cascading of Geekspeak and the Upshots for Social Cognitive Systems

Michał B. Paradowski, Łukasz Jonak|arXiv (Cornell University)|Nov 29, 2011

Language and cultural evolution19 references4 citations

TL;DR

This paper investigates how neologisms ('geekspeak') spread through social networks using a microblogging platform, applying complexity science to model cascading information diffusion. It reveals exposure thresholds and systemic dynamics in human social cognition, offering design principles for socially aware artificial cognitive systems that learn from multiple social sources rather than dyadic interactions.

ABSTRACT

Barring swarm robotics, a substantial share of current machine-human and machine-machine learning and interaction mechanisms are being developed and fed by results of agent-based computer simulations, game-theoretic models, or robotic experiments based on a dyadic communication pattern. Yet, in real life, humans no less frequently communicate in groups, and gain knowledge and take decisions basing on information cumulatively gleaned from more than one single source. These properties should be taken into consideration in the design of autonomous artificial cognitive systems construed to interact with learn from more than one contact or 'neighbour'. To this end, significant practical import can be gleaned from research applying strict science methodology to human and social phenomena, e.g. to discovery of realistic creativity potential spans, or the 'exposure thresholds' after which new information could be accepted by a cognitive agent. The results will be presented of a project analysing the social propagation of neologisms in a microblogging service. From local, low-level interactions and information flows between agents inventing and imitating discrete lexemes we aim to describe the processes of the emergence of more global systemic order and dynamics, using the latest methods of complexity science. Whether in order to mimic them, or to 'enhance' them, parameters gleaned from complexity science approaches to humans' social and humanistic behaviour should subsequently be incorporated as points of reference in the field of robotics and human-machine interaction.

Motivation & Objective

• To understand how novel linguistic expressions ('geekspeak') propagate through social networks.
• To identify systemic patterns and thresholds in human information adoption during social cascades.
• To derive parameters from human social cognition for improving artificial cognitive systems.
• To bridge insights from human social dynamics with the design of multi-agent learning systems.

Proposed method

• Analyzing real-world microblogging data to track the spread of self-invented lexemes.
• Applying complexity science methods to model emergent global dynamics from local interactions.
• Using agent-based simulations to replicate and study information diffusion patterns.
• Measuring exposure thresholds—points at which new information is accepted by cognitive agents.
• Integrating findings into models of social cognitive systems for robotics and AI.
• Comparing observed social cascades with theoretical models of collective behavior.

Experimental results

Research questions

• RQ1 What are the critical thresholds at which new linguistic innovations become socially accepted?
• RQ2 How do local interactions give rise to large-scale systemic patterns in information diffusion?
• RQ3 What role do multiple information sources play in shaping cognitive agent decision-making?
• RQ4 How can social cascading dynamics inform the design of socially intelligent artificial cognitive systems?
• RQ5 What measurable parameters from human social cognition can enhance machine learning in multi-agent environments?

Key findings

• Neologisms spread through social networks in cascading patterns that emerge from local, low-level interactions.
• A critical 'exposure threshold' exists beyond which new information is more likely to be adopted by cognitive agents.
• The propagation of geekspeak follows systemic dynamics consistent with complexity science models of collective behavior.
• Multiple information sources significantly influence the acceptance and spread of novel linguistic constructs.
• Social cascading patterns in microblogging mirror real-world cognitive processes, offering testable parameters for artificial systems.
• Findings suggest that multi-source information integration is essential for designing socially adaptive cognitive agents.