SearcharxivSearch

arXiv subjects

Paula Ebner

Publications and source records attributed to Paula Ebner.

3 recordsLinked to original sources

Love in the Age of AI: An Integrative Process Model of Romantic Human-Chatbot Relationships

The increasing ability of social chatbots to form deep and even romantic Human-Chatbot Re lationships (HCRs) has drawn growing academic attention. Yet, existing research remains fragmented, often examining individual stages such as initiation or dissolution in isolation, without tracing the full relational trajectory. Such fragmentation, however, hinders a holistic understanding of the interplay between the unique psychological and social drivers, relational dynamics, and profound emotional stakes, particularly obscuring the elements unique to ro mantic bonding. This paper addresses this gap by introducing the first empirically grounded integrative process model of the romantic HCR lifecycle. A qualitative secondary analysis of 73 user experiences, drawn from two datasets of qualitative interviews and surveys, provides the basis for a three-phase model that synthesizes established theoretical frameworks related to user needs and gratifications, HCR development, and relationship dissolution. The model demonstrates that the Initiation phase is driven by specific psychological and social determi nants that shape the needs and gratifications sought by the user. The Relationship Building phase progresses through explorative, affective and stable stages, in which users develop gen uine romantic feelings and a deeply integrated bond with the chatbot. Finally, the Ending phase reveals that when dissolution occurs, it elicits emotional and physical responses com parable to human breakups but generates unique, technology-mediated coping mechanisms, potentially leading to a recursive cycle of re-engagement.

cs.HC

10 Questions to Fall in Love with ChatGPT: An Experimental Study on Interpersonal Closeness with Large Language Models (LLMs)

Large language models (LLMs), like ChatGPT, are capable of computing affectionately nuanced text that therefore can shape online interactions, including dating. This study explores how individuals experience closeness and romantic interest in dating profiles, depending on whether they believe the profiles are human- or AI-generated. In a matchmaking scenario, 307 participants rated 10 responses to the Interpersonal Closeness Generating Task, unaware that all were LLM-generated. Surprisingly, perceived source (human or AI) had no significant impact on closeness or romantic interest. Instead, perceived quality and human-likeness of responses shaped reactions. The results challenge current theoretical frameworks for human-machine communication and raise critical questions about the importance of authenticity in affective online communication.

cs.HC

Understanding Human-Chatbot Romance: A Qualitative and Quantitative Study on Romantic Fantasy and Other Interpersonal Characteristics

LLM-based chatbots are now being specifically designed to facilitate social companionship, even romantic relationships, incorporating features that parallel human relationship dynamics. This has led a subset of users to form romantic relationships with chatbots. Understanding which interpersonal characteristics drive individuals to form intense, emotional bonds with chatbots is crucial for comprehending the potential psychological and societal impacts of romantic human-chatbot relationships. This mixed-methods study investigates psychological predictors of relationship intensity among individuals currently in romantic relationships with chatbots. Romantic and sexual fantasy, promising constructs not previously investiagted in this context, are examined alongside previously discussed factors (loneliness, anthropomorphism, attachment orientation, and sexual sensation seeking). In Study 1, quantitative data from individuals with chatbot partners (N=92) showed that romantic fantasy explained the most variance in relationship intensity, with additional contributions from anthropomorphism and avoidant attachment. Contrary to expectations, the other predictors, including loneliness, did not significantly predict intensity. In Study 2, 15 qualitative interviews illuminated how users employ romantic fantasy to enhance their relationships, describing active fantasy use to shape interactions and a desire for their chatbot to feel as human as possible. This study provides the first quantitative sample of this under-researched population, explaining who might form more intense romantic relationships with chatbots.

cs.HC