Novelty-focused weak signal detection in futuristic data: Assessing the rarity and paradigm unrelatedness of signals

Previous attempts to scan weak signals from quantitative data focus on earliness, but neglect the novel nature of signals. This study proposes an approach to novelty-focused weak signal detection from online futuristic data. For this, first, text mining is applied to extract signals in the form of keywords from futuristic data. Second, a local outlier factor is utilized to assess the rarity and paradigm unrelatedness of signals. The futuristic data is considered a source of weak signals and patent data is utilized as a proxy for existing paradigms of technological innovation. Finally, signal-portfolio maps are developed to identify the patterns of signal representations. The proposed approach helps broaden the source of weak signals and improve the sensitivity to the detection of weak signals. A case study on augmented reality technology is presented