Engagement-Driven Content Generation with Large Language Models

TL;DR

This paper introduces a reinforcement learning framework that uses simulated feedback to enable large language models to generate content that maximizes user engagement on social networks, bypassing the need for costly live experiments.

Contribution

It presents a flexible, adaptive pipeline for optimizing LLM-generated content for engagement using simulated feedback, applicable to complex social network scenarios.

Findings

LLMs can effectively generate engaging social content under various conditions.

The framework is adaptable to different engagement models and opinion distributions.

Experimental results demonstrate the potential of LLMs in social engagement tasks.

Abstract

Large Language Models (LLMs) demonstrate significant persuasive capabilities in one-on-one interactions, but their influence within social networks, where interconnected users and complex opinion dynamics pose unique challenges, remains underexplored. This paper addresses the research question: \emph{Can LLMs generate meaningful content that maximizes user engagement on social networks?} To answer this, we propose a pipeline using reinforcement learning with simulated feedback, where the network's response to LLM-generated content (i.e., the reward) is simulated through a formal engagement model. This approach bypasses the temporal cost and complexity of live experiments, enabling an efficient feedback loop between the LLM and the network under study. It also allows to control over endogenous factors such as the LLM's position within the social network and the distribution of opinions on a given topic. Our approach is adaptive to the opinion distribution of the underlying network and agnostic to the specifics of the engagement model, which is embedded as a plug-and-play component. Such flexibility makes it suitable for more complex engagement tasks and interventions in computational social science. Using our framework, we analyze the performance of LLMs in generating social engagement under different conditions, showcasing their full potential in this task. The experimental code is publicly available at https://github.com/mminici/Engagement-Driven-Content-Generation.