TwIPS: A Large Language Model Powered Texting Application to Simplify Conversational Nuances for Autistic Users
Rukhshan Haroon, Fahad Dogar
TL;DR
TwIPS addresses the challenge of conveying and interpreting emotional tone and non-literal language in text among autistic users by introducing three LLM-powered features: Interpret to analyze incoming messages, Preview to anticipate recipient reactions, and Suggest to propose softer alternative phrasings. An in-lab study with eight autistic participants evaluates usability, autonomy, and perceived usefulness, showing TwIPS facilitates clarifications and reflective writing while highlighting needs for trust, personalization, and user control. The work contributes a design and evaluation framework for AI assisted, neurodiversity aware text communication and discusses implications for privacy, customization, and broader applicability beyond autism. Overall, TwIPS demonstrates how AI mediated writing can augment autonomy in everyday texting, with careful attention to user agency, trust, and adaptable personalization in real world settings.
Abstract
Autistic individuals often experience difficulties in conveying and interpreting emotional tone and non-literal nuances. Many also mask their communication style to avoid being misconstrued by others, spending considerable time and mental effort in the process. To address these challenges in text-based communication, we present TwIPS, a prototype texting application powered by a large language model (LLM), which can assist users with: a) deciphering tone and meaning of incoming messages, b) ensuring the emotional tone of their message is in line with their intent, and c) coming up with alternate phrasing for messages that could be misconstrued and received negatively by others. We leverage an AI-based simulation and a conversational script to evaluate TwIPS with 8 autistic participants in an in-lab setting. Our findings show TwIPS enables a convenient way for participants to seek clarifications, provides a better alternative to tone indicators, and facilitates constructive reflection on writing technique and style. We also examine how autistic users utilize language for self-expression and interpretation in instant messaging, and gather feedback for enhancing our prototype. We conclude with a discussion around balancing user-autonomy with AI-mediation, establishing appropriate trust levels in AI systems, and customization needs if autistic users in the context of AI-assisted communication