Visualization in the preprocessing phase: an interview study with enterprise professionals
This work addresses the specific problem of improving visualization support for data preprocessing in enterprise settings, though it is incremental as it builds on existing interview studies.
The study conducted semi-structured interviews with thirteen enterprise data analysts to understand challenges and opportunities in the preprocessing phase of data mining workflows, resulting in a list of ten insights that consolidate findings from related works.
The current information age has increasingly required organizations to become data-driven. However, analyzing and managing raw data is still a challenging part of the data mining process. Even though we can find interview studies proposing design implications or recommendations for future visualization solutions in the data mining scope, they cover the entire workflow and do not fully focus on the challenges during the preprocessing phase and on how visualization can support it. Moreover, they do not organize a final list of insights consolidating the findings of other related studies. Hence, to better understand the current practice of enterprise professionals in data mining workflows, in particular during the preprocessing phase, and how visualization supports this process, we conducted semi-structured interviews with thirteen data analysts. The discussion about the challenges and opportunities based on the responses of the interviewees resulted in a list of ten insights. This list was compared with the closest related works, improving the reliability of our findings and providing background, as a consolidated set of requirements, for future visualization research papers applied to visual data exploration in data mining. Furthermore, we provide greater details on the profile of the data analysts, the main challenges they face, and the opportunities that arise while they are engaged in data mining projects in diverse organizational areas.