Characters and their interactions are central to the fabric of narratives, playing a crucial role in developing readers’ social cognition. In this paper, we introduce a novel annotation framework that distinguishes between five types of character interactions, including bilateral and unilateral classifications. Leveraging the crowd-sourcing framework of citizen science, we collect a large dataset of manual annotations (N=13,395). Using this data, we explore how genre and audience factors influence social network structures in a sample of contemporary books. Our findings demonstrate that fictional narratives tend to favor more embodied interactions and exhibit denser and less modular social networks. Our work not only enhances the understanding of narrative social networks but also showcases the potential of integrating citizen science with NLP methodologies for large-scale narrative analysis.

Non-Player Characters (NPCs) significantly enhance the player experience in many games. Historically, players’ interactions with NPCs have tended to be highly scripted, to be limited to natural language responses to be selected by the player, and to not involve dynamic change in game state. In this work, we demonstrate that use of a few example conversational prompts can power a conversational agent to generate both natural language and novel code. This approach can permit development of NPCs with which players can have grounded conversations that are free-form and less repetitive. We demonstrate our approach using OpenAI Codex (GPT-3 finetuned on GitHub), with Minecraft game development as our test bed. We show that with a few example prompts, a Codex-based agent can generate novel code, hold multi-turn conversations and answer questions about structured data. We evaluate this application using experienced gamers in a Minecraft realm and provide analysis of failure cases and suggest possible directions for solutions.