Paper: Towards Olfactory Information Extraction from Text – A Case Study on Detecting Smell Experiences in Novels

This weekend, Marieke van Erp presented a paper on extracting olfactory information from English text at the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, organised in conjunction with COLING 2020. The paper was presented in a poster presentation, sadly not in Barcelona, but in a session.

For this paper, we did a first set of experiments into how we can best recognise references to smell in texts, which is an important task in Odeuropa’s Work Package 3.  For this paper, we first created an annotated dataset, i.e. a set of texts in which humans (= Odeuropa team members) marked whether the text described a reference to a smell. We then created patterns based on a set of smell related words from the Cambridge dictionary of English to such as ‘smells like X’ and ‘a Y fragrance’ where X and Y can stand for nouns and adjectives. We ran the patterns over a large set of texts to see if we could find more expressions referring to smells in text as compared to only using the dictionary smell keywords, and our experiments showed that patterns indeed worked better than keywords. In Odeuropa, we will further build on this, as well as try out other methods (such as machine learning) to recognise references to smells in Latin, English, Italian, German, French, Dutch, and Slovene texts from 1600 – 1920 across different genres.

This research paper was based on the Ryan Brate’s MSc thesis work which he did for the University of Amsterdam’s Data Science degree programme under the supervision of prof. dr. Paul Groth and dr. Marieke van Erp. Full citation:

Brate, Ryan, Paul Groth, and Marieke van Erp. “Towards Olfactory Information Extraction from Text: A Case Study on Detecting Smell Experiences in Novels.” In Proceedings of the The 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pp. 147-155. 2020.

Creating the visual identity of a project on smell

How do you design a logo for an academic research project that covers olfactory heritage, history, artificial intelligence….and looks good?  Caro Verbeek, olfactory art historian, interviewed Kate McLean lecturer, artist, designer, and researcher of Sensory Maps on how she created the visual logo for Odeuropa.

Dr. Kate McLean


You are famous for designing smell maps and guiding scent walks. What exactly are these and why do you engage in them?

Smell maps, or smellscape maps, are depictions of human olfactory experience in a place at a moment in time. The data (smells) depicted on the maps is collected by inhabitants of the city being mapped through a process known as smell walking. Smell walking is a walk in which you register what you smell in preference to what you see or hear – a deliberate foregrounding of the nose as the sense of primary information (for a short period of time).

You designed a visual identity or logo for Odeuropa. What were the major challenges?

The major challenge in designing a logo for Odeuropa was how to depict a project at its onset… the Odeuropa project was funded precisely because it covers ground not previously explored; use of AI, focus on smell, digital and physical, history and future archive. The other challenge was to understand the smellmark as a part of the identity and to complement what Frank Bloem’s work communicates.

How did you afford the logo ‘smellability’?

The logo’s smellability derives from its wafting forms that make up an “O” and an “e” – the fluid, soft edged strokes are designed to resemble smoke, which is the closest visual conceptual link humans have for smell – we can imagine smoke manifest and swirl. The green and purple colours are complementary to signify the various dualities within the project.

Your logo is part of a multi-sensory whole. How do the visual aspects connect to the olfactory ones (by Frank Bloem)?

Frank Bloem’s smellmark takes its inspiration from the letters of the word Odeuropa, as does the logo… the connection between visual and olfactory is through letter forms – apposite for a project which will analyse texts.