People visiting or moving to a new city often struggle to understand local vibes and everyday routines. Short-form videos on TikTok capture these local stories, but people still have to jump between chatbots, maps, and apps to turn them into concrete plans. We introduce PlaceWeave, a human-centered trip-planning system that foregrounds a place's ''localness''. PlaceWeave builds a place knowledge graph from TikTok videos and uses it to ground all AI features: the conversational assistant, localness attributes on the map, and the route planner all draw on graph evidence. The interface combines an interactive map, an evidence-backed Insights Panel, and tools for organizing discoveries and composing itineraries in a single linked workspace. We validate the attributes and run a within-subjects study with 18 participants, comparing PlaceWeave to a baseline using separate chat, map, video, and canvas tools. PlaceWeave helps people create more local-feeling plans, better understand neighborhood character and trade-offs, and avoid fragmented workflows. We show how localness-aware, graph-grounded AI can support more community-sensitive placemaking technologies.
ACM CHI Conference on Human Factors in Computing Systems