Towards Olfactory Information Extraction from Text: A Case Study on Detecting Smell Experiences in Novels
This work provides a novel method for extracting olfactory information from text, which could be valuable for researchers studying cultural and societal perceptions of smell.
This paper addresses the problem of identifying 'smell experiences' in text, which are descriptions of smells. The authors developed two semi-supervised approaches to extract these references from English literature, achieving significantly better performance than a keyword-based baseline.
Environmental factors determine the smells we perceive, but societal factors factors shape the importance, sentiment and biases we give to them. Descriptions of smells in text, or as we call them `smell experiences', offer a window into these factors, but they must first be identified. To the best of our knowledge, no tool exists to extract references to smell experiences from text. In this paper, we present two variations on a semi-supervised approach to identify smell experiences in English literature. The combined set of patterns from both implementations offer significantly better performance than a keyword-based baseline.