Investigating a Mixed-Initiative Workflow for Digital Mind-Mapping

Abstract

In this paper, we report on our investigation of human-AI collaboration for mind-mapping. We specifically focus on problem exploration in pre-conceptualization stages of early design. Our approach leverages the notion of query expansion—the process of refining a given search query for improving information retrieval. Assuming a mind-map as a network of nodes, we reformulate its construction process as a sequential interaction workflow wherein a human user and an intelligent agent take turns to add one node to the network at a time. Our contribution is the design, implementation, and evaluation of algorithm that powers the intelligent agent (IA). This paper is an extension of our prior work (Chen et al., 2019, “Mini-Map: Mixed-Initiative Mind-Mapping Via Contextual Query Expansion,” AIAA Scitech 2020 Forum, p. 2347) wherein we developed this algorithm, dubbed Mini-Map, and implemented a web-based workflow enabled by ConceptNet (a large graph-based representation of “commonsense” knowledge). In this paper, we extend our prior work through a comprehensive comparison between human-AI collaboration and human-human collaboration for mind-mapping. We specifically extend our prior work by: (a) expanding on our previous quantitative analysis using established metrics and semantic studies, (b) presenting a new detailed video protocol analysis of the mind-mapping process, and (c) providing design implications for digital mind-mapping tools.

Idea generation with Technology Semantic Network

“…Other than WordNet that was collectively built via direct human efforts, a few other free online knowledge bases have also been employed in new design ideation methods or tools. For example, Chen and Krishnamurthy (2020) proposed an interactive procedure to retrieve words and terms in ConceptNet to inspire designers. ConceptNet (Speer et al, 2017) is a large public knowledge graph automatically extracted from Wikipedia, built and maintained at MIT Media Lab.…”

Semantic Networks for Engineering Design: A Survey

“…Han et al (2020) also proposed to evaluate new ideas based on the semantic similarity of their elemental concepts using ConceptNet. Chen and Krishnamurthy (2020) proposed an interactive procedure to retrieve words and terms in ConceptNet to inspire designers. Camburn et al (2019) proposed a set of new metrics for automatic evaluation of the natural language descriptions of a large number of crowdsourced design ideas, and their evaluation was based on the Freebase (Bollacker et al, 2008), another large knowledge database managed by Google.…”

Design Knowledge Representation With Technology Semantic Network

“…Network metrics have provided a medium to derive useful design-related insights from the structure of the graphs, and various layout methods have provided ways of representing the design-related data in an easily comprehensible way (Lim et al, 2016;. For example, network visualizations have been utilized to represent the whole technology space to support innovation and competitive intelligence (Luo et al, 2017(Luo et al, , 2018Sarica, Yan, et al, 2020), show the relations between components and subsystems to evalute designs (He and Luo, 2017;Pasqual and De Weck, 2012;Sosa et al, 2007) and inform design decisions (Kim and Kim, 2012;Sosa et al, 2007), discover the patterns of design activities (Alstott et al, 2017;Cash et al, 2014;Cash and Štorga, 2015), reveal the structure of design document repositories to guide retrievals (Fu et al, 2013;Luo et al, 2021), and represent mind maps (Camburn, Arlitt, et al, 2020;Camburn, He, et al, 2020) and concept networks (Chen et al, 2019;Chen and Krishnamurthy, 2020;Liu et al, 2020;Sarica et al, 2019Sarica et al, , 2021Shi et al, 2017;Song, Evans, et al, 2020;Souili et al, 2015) for design ideation uses. On the other hand, a few studies explored other visualization methods such as word-clouds (He, Camburn, Liu, et al, 2019; based on design description texts.…”