Enhancing user creativity: Semantic measures for idea generation

Abstract

Human creativity generates novel ideas to solve real-world problems. This thereby grants us the power to transform the surrounding world and extend our human attributes beyond what is currently possible. Creative ideas are not just new and unexpected, but are also successful in providing solutions that are useful, efficient and valuable. Thus, creativity optimizes the use of available resources and increases wealth. The origin of human creativity, however, is poorly understood, and semantic measures that could predict the success of generated ideas are currently unknown. Here, we analyze a dataset of design problem-solving conversations in real-world settings by using 49 semantic measures based on WordNet 3.1 and demonstrate that a divergence of semantic similarity, an increased information content, and a decreased polysemy predict the success of generated ideas. The first feedback from clients also enhances information content and leads to a divergence of successful ideas in creative problem solving. These results advance cognitive science by identifying real-world processes in human problem solving that are relevant to the success of produced solutions and provide tools for real-time monitoring of problem solving, student training and skill acquisition. A selected subset of information content (IC Sanchez-Batet) and semantic similarity (Lin/Sanchez-Batet) measures, which are both statistically powerful and computationally fast, could support the development of technologies for computer-assisted enhancements of human creativity or for the implementation of creativity in machines endowed with general artificial intelligence.

Assessing Concept Novelty Potential with Lexical and Distributional Word Similarity for Innovative Design

“…It is also used to quantify the similarity of design concepts written in linguistic representation such as function, e.g. (Cheong et al, 2017) , and to analyze the characteristics of idea generation process (Georgiev and Georgiev, 2018). There are two approaches to measure word similarity: lexical approach and distributional approach.…”

Semantic Measures for Enhancing Creativity in Design Education

“…Hence, abstraction is considered to be an important characteristic of creative idea generation. In the language and thinking domain, information content (IC) is defined as the amount of information conveyed by a particular unit of language in a specific context (Georgiev and Georgiev, 2018). IC measures the degree of informativeness of a unit.…”

“…A document-level semantic similarity was used to quantify how alike two topics in design are (Hill et al, 2001). Georgiev and Georgiev (2018) showed that semantic similarity measures can be useful in the identification and representation of essential processes in design thinking. Only a few studies focused on the relationship between semantic analysis approach and creativity.…”

“…On the other hand, to the best of our knowledge, not many semantic approach-based researches were carried out to investigate design creativity in real-world settings. Few exceptions are Georgiev and Georgiev (2018), Georgiev, Nagai, and Taura (2010), Georgiev and Taura, (2014), Taura et al (2012) and Yamamoto et al (2009). Existing methods related to the study of creativity, such as linkography (Goldschmidt, 2014), are laborious, effortful, and narrow in the sense that are largely focused on design ideas, rather than on the semantic content of the verbalisations.…”

“…First, it uses a number of semantic measures that enable the quantification of fundamental phenomena in design, cognitive psychology and linguistics. Such measures, which showed to be successful to study ideation in design problem, include polysemy, abstraction, information content (IC) and semantic similarity (Georgiev and Georgiev, 2018). Second, it applies systematic and domain independent representation of words (i.e., WordNet database).…”