Qualitative Data Visualization Dashboard

定性数据可视化仪表板

• 批准号: 569170-2021
• 负责人: Rajabiyazdi, Fatemeh
• 金额: $ 1.46万
• 依托单位: Carleton University
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=720693
• 关键词: Qualitative; Data; Visualization; Dashboard

Existing data visualization solutions provide robust quantitative data representations using standard charts-such as bar charts and pie charts. However, few visualizations exist for representing qualitative data, including descriptive and conceptual data collected via open-ended survey questions or comments boxes, harvested from websites or social media updates, or transcribed from other sources such as call centre calls or focus groups. Regardless of the source, the common unifying thread is that the data does not conform to a predetermined taxonomy or format-rather, it is a free-flowing stream of opinions or facts in the publisher's own words.The existing visualization tools are insufficient when it comes to conveying insight with qualitative data. As a result, qualitative data visualization representations are often custom implementations that are difficult and expensive to reuse. Through this project, we aim to design and implement a qualitative data visualization dashboard that provides audiences with a way to gain insights from the data while maintaining a level of generality and customization options that make it applicable to a variety of use cases. The initial phase will focus on creating a set of visualizations (i.e., charts) to represent datasets primarily comprised of natural language data. The combination of these visualizations will provide a visual narrative that will communicate various meanings and insights hidden in the data. The final solution will be deployed and integrated into the NovaceneAI Platform, a tool designed for analysts and subject matter experts without a data science background. The ability for these users to customize the dashboard will provide the autonomy necessary to create different visualizations suitable for a variety of use cases.

现有的数据可视化解决方案使用标准图表（如条形图和饼图）提供健壮的定量数据表示。然而，用于表示定性数据的可视化很少，包括通过开放式调查问题或评论框收集的描述性和概念性数据，从网站或社交媒体更新中收集，或从呼叫中心呼叫或焦点小组等其他来源转录。不管来源是什么，共同的线索是数据不符合预定的分类或格式，而是用出版商自己的话来说，它是一个自由流动的观点或事实流。当涉及到用定性数据传达洞察力时，现有的可视化工具是不够的。因此，定性数据可视化表示通常是自定义实现，重用起来既困难又昂贵。通过这个项目，我们的目标是设计和实现一个定性的数据可视化仪表板，为受众提供一种从数据中获得洞察力的方法，同时保持一定程度的通用性和自定义选项，使其适用于各种用例。初始阶段将专注于创建一组可视化（即图表）来表示主要由自然语言数据组成的数据集。这些可视化的组合将提供一种视觉叙事，将传达隐藏在数据中的各种含义和见解。最终的解决方案将部署并集成到NovaceneAI平台中，该平台是为没有数据科学背景的分析师和主题专家设计的工具。这些用户自定义仪表板的能力将为创建适合各种用例的不同可视化提供必要的自主权。