Data mining and knowledge graphs as a backbone for advanced olfactory experiences

Lisena, Pasquale; van Erp, Marieke; Bembibre, Cecilia; Leemans, Inger

Our senses are the gateways to our memories and emotions and can provide rich experiences when used in museum or retail settings. However, information about sensory experiences is often dispersed in different data sources, or not yet machine processable. In this position paper, we present our vision on mining olfactory data from text and integrating it with structured olfactory sources (e.g. chemistry databases, industry odour
descriptors) to advance our understanding of how smells are represented in texts and structured data, as well as to leverage this information to create more advanced multisensory experiences. In particular, we propose Knowledge Graph technologies for enabling data re-using, enrichment with background information, and AI applications. In addition, we review the challenges of curating, interpreting and presenting smells in instances where the source or/and the original situational context are not present and discuss the relevance of a scent significance preservation framework.

Data Science
Eurecom Ref:
© ACM, 2021. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in
See also: