Comparing How a Chatbot References User Utterances from Previous Chatting Sessions: An Investigation of Users' Privacy Concerns and Perceptions
This work addresses privacy and engagement trade-offs in chatbot design for users and developers, offering incremental insights into referencing formats.
The study investigated how chatbots referencing previous conversations affect user engagement and privacy, finding that verbatim and paraphrased references increased perceived intelligence and engagement, but verbatim references raised privacy concerns among 169 participants in a longitudinal study.
Chatbots are capable of remembering and referencing previous conversations, but does this enhance user engagement or infringe on privacy? To explore this trade-off, we investigated the format of how a chatbot references previous conversations with a user and its effects on a user's perceptions and privacy concerns. In a three-week longitudinal between-subjects study, 169 participants talked about their dental flossing habits to a chatbot that either, (1-None): did not explicitly reference previous user utterances, (2-Verbatim): referenced previous utterances verbatim, or (3-Paraphrase): used paraphrases to reference previous utterances. Participants perceived Verbatim and Paraphrase chatbots as more intelligent and engaging. However, the Verbatim chatbot also raised privacy concerns with participants. To gain insights as to why people prefer certain conditions or had privacy concerns, we conducted semi-structured interviews with 15 participants. We discuss implications from our findings that can help designers choose an appropriate format to reference previous user utterances and inform in the design of longitudinal dialogue scripting.