Good design relies upon the generation of good ideas, but producing ideas, especially creative ones, is increasingly challenging. This may be due to limited relevant information, lack of creative skills, design fixation, or as a result of too many previously existing ideas. Conventional creativity tools, such as brainstorming and TRIZ, as well as advanced methods, such as design-by-analogy, are often employed by designers for idea generation to alleviate some of these challenges. In recent years, computational creativity tools have emerged to support creative idea generation. However, most of these computational tools are data-driven, and thereby employ various databases, for example, existing databases such as the ConceptNet containing past common-sense knowledge, and customized ones containing limited information. The limitations of these databases have constrained the capability of the computational creativity tools. Social media platforms, such as Twitter and Wikipedia, which allow users to create web-based content, have been reported to have billions of users. It can be considered a huge ‘unorganized’ database of information created by a crowd. However, to date little work has been done on the utilization of such crowd-generated knowledge from social media to support actual design activities, especially during the early stages of the design process. In this paper, the authors propose a computational approach to retrieve, process, and reuse the textual knowledge from social networks to prompt designers’ creative mind in producing ideas for new product design and development. They also propose a novel approach to construct crowd knowledge databases, which can be employed by computational tools, as well as used individually, for supporting creative idea generation. A case study involving the use of an existing social media analysis tool to construct a crowd database for helping designers produce ideas has been conducted to provide insights on implementing the proposed approach for creative idea generation.
展开▼
