InTREND: An Interactive Tool for Reflective Data Exploration Through Natural Discourse

The goal of this paper is to support users in exploring huge amounts of data for the purpose of decision-making and problem-solving. Our approach is to design human-computer interaction as a natural discourse between the user who explores the data, and the system that interprets the user’s query, retrieves data based on the query, and presents the result. The InTREND system supports this type of interaction by (1) interpreting the user’s query represented in a natural language, (2) composing a statistical chart based on the query and the retrieved data, and (3) presenting the graph with animation. InTREND encourages iterative exploration by maintaining the context of past interactions and using this context to improve discourse with the user.