Facilitating Continuous Text Messaging in Online Romantic Encounters by Expanded Keywords Enumeration

ABSTRACT An increasing number of people are looking for romantic partners online. Many of them first converse online before deciding whether or not to meet in-person. However, it is often challenging to have smooth and continuous conversations online with someone who they have never met in person. To handle this problem, we built a proof-of-concept system, Tomi, that dynamically suggests various conversation topic seeds related to the latest received messages in real-time. It selects a keyword from an incoming message and returns five contextually relevant topic seeds. In a qualitative study with eight dyads that simulated the common setting of online match-making, users could continue their conversations either by directly or indirectly utilizing the suggested topic seeds. Also, our system boosted their confidence during the chat. Lastly, we analyzed the trade-offs between several design alternatives and presented our reflections on a system supporting continuous conversations with diverse topics.