How does anthropomorphism improve human-AI interaction satisfaction: a dual-path model

With the development of artificial intelligence technology, the application of anthropomorphism has been established as a good design principle. However, the effectiveness of anthropomorphism in smart home assistants is still unclear, as is the mechanism influencing interaction satisfaction. Therefore, we have categorized the anthropomorphic cues of smart home assistants into four dimensions: visual, identity, emotional, and auditory, and constructed a dual-path influence mechanism model of anthropomorphism on interaction satisfaction. Furthermore, we also consider the different influences of different usage contexts. Through two experimental studies, the results show that, in the intimacy influence path, the emotional cue and auditory cue can directly improve interaction satisfaction, and they can further improve interaction satisfaction by affecting intimacy. However, the visual cue has no significant direct effect on interaction satisfaction. The visual cue mainly improves interaction satisfaction through the intermediate effect of intimacy. In the privacy invasion influence path, the emotional cue and auditory cue also further affect interaction satisfaction by affecting privacy invasion. However, the impact of the visual cue and identity cue on privacy invasion was not valid. The study is expected to provide practical guidance for product designers to realize the long-term feasibility and sustainability of products.