Characterizing Automated Data Insights
This work addresses a foundational gap for researchers and developers in data analysis tools, but it is incremental as it synthesizes existing literature.
The paper tackled the lack of structured understanding of 'insight' in automated data recommendation tools by conducting a systematic review, resulting in a proposed taxonomy of 12 insight types and four purposes.
Many researchers have explored tools that aim to recommend data insights to users. These tools automatically communicate a rich diversity of data insights and offer such insights for many different purposes. However, there is a lack of structured understanding concerning what researchers of these tools mean by "insight" and what tasks in the analysis workflow these tools aim to support. We conducted a systematic review of existing systems that seek to recommend data insights. Grounded in the review, we propose 12 types of automated insights and four purposes of automating insights. We further discuss the design opportunities emerged from our analysis.