Do What I Mean, Not What I Say! Design Considerations for Supporting Intent and Context in Analytical Conversation

Description: 

Natural language can be a useful modality for creating and interacting with visualizations but users often have unrealistic expectations about the intelligence of natural language systems. The gulf between user expectations and system capabilities may lead to a disappointing user experience. So—if we want to engineer a natural language system, what are the requirements around system intelligence? This work takes a retrospective look at how we answered this question in the design of Ask Data, a natural language interaction feature for Tableau. We examine two factors contributing to perceived system intelligence: the system’s ability to understand the analytic intent behind an input utterance and the ability to interpret an utterance contextually (i.e. taking into account the current visualization state and recent actions). Our aim was to understand the ways in which a system would need to support these two aspects of intelligence to enable a positive user experience. We first describe a pre-design Wizard of Oz study that offered insight into this question and narrowed the space of designs under consideration. We then reflect on the impact of this study on system development, examining how design implications from the study played out in practice. Our work contributes insights for the design of natural language interaction in visual analytics as well as a reflection on the value of pre-design empirical studies in the development of visual analytic systems.

Example 'analytical conversation' from our study showing how intent could drive visualization responses for a dataset of Titanic passengers. Following an initial utterance (a), an anaphoric reference conveys an implicit intent to retain context (b). Attributes Children Aboard? and Survived? are retained, while Sex and Age are added in a way that preserves the previous chart structure. In (c), 'correlation' suggests an implicit intent for a new visualization such as a heat map to depict relationships between attributes %survived, Age, and Fare.

 

Video link 

 

Authors: 
Melanie Tory and Vidya Setlur
Publication Date: 
Sunday, October 20, 2019
Publication Information: 
IEEE Conference on Visual Analytics Science and Technology (VAST), October 20-25, 2019