Search papers, labs, and topics across Lattice.
This study investigates how repeated interactions with a memory-augmented conversational AI shape user relationships over time, involving 24 participants across 10 sessions. Key findings reveal that while conversational quality enhances immediate enjoyment, it does not influence future interactions, whereas perceived memory, influenced by prior relational states, plays a crucial role in fostering self-disclosure and subsequent enjoyment. Additionally, the research identifies discrete relational turning points鈥攂oth surges and crashes鈥攊n user experiences, which can be predicted by multimodal behavioral cues, highlighting the complex dynamics of human-AI relationships.
Relationships with conversational AIs evolve through both gradual accumulation of familiarity and sudden relational turning points that can be anticipated through user behavior.
As conversational AI systems are designed for repeated use, a central question is how a series of interactions becomes a relationship. We present a longitudinal multimodal study of a memory-augmented conversational agent (24 participants x 10 sessions), in which participants rated five relational constructs -- familiarity, self-disclosure, perceived memory, conversational quality, and enjoyment -- after each session. Two complementary dynamics emerge. First, conversational quality strongly shapes how enjoyable a session feels in the moment but does not carry forward across sessions, whereas perceived memory is relationally conditioned -- predicted by prior relational state rather than reflecting system capability alone -- and it shapes later enjoyment indirectly, via subsequent self-disclosure. Second, relationships are punctuated by discrete turning points -- crashes and surges -- that are partially traceable in multimodal behavior and open different intervention windows: surges are more behaviorally detectable in the moment, enjoyment surges persist more reliably than enjoyment crashes recover, and some crashes are better forecast from person-specific behavioral drift than detected after they have already occurred. Together, the findings suggest that longitudinal human-AI relationships are built through both slow accumulation and abrupt turning points.
