The HeyTAP conversational agent

In the Internet of Things era, users are willing to personalize the joint behavior of their smart devices and online service by means of IF-THEN rules. Unfortunately, how to make such a personalization effective and appreciated is still largely unknown, and defining IF-THEN rules is a complex task for end users.

The paper HeyTAP: Bridging the Gaps Between Users’ Needs and Technology in IF-THEN Rules via Conversation presents HeyTAP,a conversational and semantic-powered trigger-action programming platform able to map abstract users’ needs to executable IF-THEN rules.

By interacting with a conversational agent, the user communicates to HeyTAP her envisioned rules and related preferences in natural language. User’s inputs, along with contextual and semantic information related to the available connected entities, are then used to map a set of IF-THEN rules that satisfies the user’s needs. An exploratory study on 8 end users preliminary confirms the effectiveness and the appreciation of the approach, and shows that HeyTAP can successfully guide users from their needs to specific rules.

The paper has been accepted for presentation as part of the International Conference on Advanced Visual Interfaces (AVI '20), that will take place on the island of Ischia (Italy), from September 28 to October 2, 2020.

Additional information: