Classifying Creativity: Applying Machine Learning Techniques to Divergent Thinking EEG Data

Abstract

<p>Prior research has shown that greater EEG alpha power (8-13 Hz) is characteristic of more creative individuals, and more creative task conditions. The present study investigated the potential for machine learning to classify more and less creative brain states. Participants completed an Alternate Uses Task, in which they thought of Normal or Uncommon (more creative) uses for everyday objects (e.g., brick). We hypothesized that alpha power would be greater for Uncommon (vs. Common) uses, and that a machine learning (ML) approach would enable the reliable classification data from the two conditions. Further, we expected that ML would be successful at classifying more (vs. less) creative individuals. As expected, alpha power was significantly greater for the Uncommon than for the Normal condition. Using spectrally weighted common spatial patterns to extract EEG features, and quadratic discriminant analysis, we found that classification accuracy for the two conditions varied widely among individuals, with a mean of 63.9%. For more vs. less creative individuals, 82.3% classification accuracy was attained. These findings indicate the potential for broader adoption of machine learning in creativity research.</p>

Brain activation during the observation of real soccer game situations predicts creative goal scoring

“…, 2018 ). The strong impact of the early stages of the creative thinking process on the ideation outcome might be one reason why Stevens and Zabelina (2020) reported a good discrimination between more and less creative brain states at a very early time window by means of machine learning of EEG data. The current findings are in accordance with these observations and underline the value of automatic and spontaneous modes of thinking for creative cognition ( Mednick, 1962 ; Benedek and Jauk, 2018 ).…”

Decoding motor expertise from fine‐tuned oscillatory network organization

“…The present study is not without limitations. First, our sample size was rather small, although not smaller than those reported in similar EEG studies using oscillatory features for binary classification of individuals varying in their learning style (Jawed, Amin, Malik, & Faye, 2019) and other traits (Stevens & Zabelina, 2020). A recent state-of-the-art comparison of classification algorithms (Zhang, Liu, Zhang, & Almpanidis, 2017) has shown that XGBoost, the algorithm implemented here, can be effective with small and large training sets, outperforming in all cases other more popular classifiers.…”

An EEG study to understand semantic and episodic memory retrieval in creative processes

“…Thirty Chinese participants (15 female, 15 male; aged 20 -25) were recruited for this study (Stevens Jr & Zabelina, 2020). This sampling number was decided based on existing research (Cash et al, 2022) of Stevens Jr and Zabelina (2020), where thirty participants were recruited and EEG were used to understand participants' creative processes. All participants were professionals in industrial design or product design.…”