Ten Years of the NRC Word-Emotion Association Lexicon

Ten years back, on May 8th 2010, with some anticipation and lots of excitement, Peter Turney and I introduced the NRC Word-Emotion Association Lexicon. So grateful that, over the years, so many people have put their hopes and trust in it. Such joy to see them boldly shine a light on the human condition — the positives and the negatives; not shying away even from sadness, fear, and anger.

Here are ten favorites to mark the ten years:

Photo credit: Tengyart

Note: This is an eclectic mix of serious academic research, innovative art, and amateur data analysis, created simply as a microcosm of the diverse uses of the emotion lexicon.

Note: The NRC Word-Emotion Association Lexicon (often shortened to NRC Emotion Lexicon, and originally called EmoLex) is a list of English words and their manually annotated associations with eight basic emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) and two sentiments (negative and positive). Translations of the lexicon in other languages are available. The data and interactive visualizations are available through the project home page. You can also find other research projects on my webpage.

Papers:

1. Wishing Wall: An #Art Piece on Wishes and Hopes

Year: 2014

Introduction of Wishing Wall, created by by Varvara and Mar:

Project Page:

Quote:

There are a number of traditions [on] how to make a wish, for example, one should make a wish when blowing the candles on birthday cake, when a year is changing, by throwing a coin in a fountain and much more. Making a wish is always connected to a magic, at the same time there is no visual manifestation nor any continuity after a wish is made.

Wishing Wall looks at re-imagining how we share our innermost wishes with the world. What if you could say your wish out loud and have it magically released into the world for people to see? In this piece spoken words are transformed into butterflies that are diverse in form and colour as they represent the sentiment of the spoken words.

Wishing Wall was displayed in the Barbican Centre London, Tekniska Museet Stockholm, Onassis Cultural Centre Athens, and Zorlu Centre Istanbul.

2. The Shapes of Stories

Years: 2011, 2014

There is no reason why the simple shapes of stories can’t be fed into computers. They are beautiful shapes.

— Kurt Vonnegut in his 1981 autobiography Palm Sunday

Tracking Emotions in Novels and Fairy Tales by Saif M. Mohammad
Year: 2011

Paper:

Media:

Quote:

Literary texts, such as novels, fairy tales, fables, romances, and epics have long been channels to convey emotions, both explicitly and implicitly…
In this paper, we show how sentiment analysis can be used in tandem with effective visualizations to quantify and track emotions in both individual books and across very large collections.

Matthew Jockers on the Relationship between Sentiment and Plot Arcs
Year: 2014

You may also be interested in this paper (that does not use EmoLex):
Year: 2016

3. TransProse: Music that Captures the Emotional Arcs in Novels

Year: 2014

Paper with Hannah Davis:

Quote:

Music and literature have an intertwined past. It is believed that they originated together (Brown,1970), but in time, the two have developed into separate art forms that continue to influence each other. Music, just as prose, drama, and poetry, is often used to tell stories. Opera and ballet tell stories through music and words, but even instrumental music, which is devoid of words, can have a powerful narrative form (Hatten, 1991). Mahler’s and Beethoven’s symphonies, for example, are regarded as particularly good examples of narrative and evocative music (Micznik, 2001).

In this paper, for the first time, we present a method to automatically generate music from literature. Specifically, we focus on novels and generate music that captures the change in the distribution of emotion words.

Click to play the music:

Peter Pan
Heart of Darkness

Media:

Click to play the symphony orchestra, inspired by the music from TransProse, performed under the glass of the Louvre museum in Paris on Sept. 20, 2016.

4. Angry Trump, Happy Trump

Year: 2016

Blog Post by by David Robinson:

Quote:

this weekend I saw a hypothesis about Donald Trump’s twitter account that simply begged to be investigated with data: When Trump wishes the Olympic team good luck, he’s tweeting from his iPhone. When he’s insulting a rival, he’s usually tweeting from an Android. Is this an artifact showing which tweets are Trump’s own and which are by some handler?

Media:

5. Emotions in Poems

Year: 2020

Paper with Will E. Hipson on understanding developmental trends through emotions in poems written by children:

Quote:

Adults, adolescents, and even young children use language to make sense of their feelings and to share them with others (Lindquist et al., 2015)…

Children live rich and varied emotional lives. Over the course of development, the way children express, experience, and communicate their emotions changes (Bailen etal., 2019; Thompson, 1991). Understanding these changes is instrumental in promoting healthy socio-emotional functioning across all stages of development.

Paper on Poetry Generation by Brendan Bena and Jugal Kalita:

Media:

6. City Maps with Sounds and Emotions

Year: 2016

Paper:

Quote:

Urban sound has a huge influence over how we perceive places. Yet, city planning is concerned mainly with noise, simply because annoying sounds come to the attention of city officials in the form of complaints, while general urban sounds cannot be easily captured at city scale. To capture both unpleasant and pleasant sounds, we propose a new methodology that relies on tagging information of georeferenced pictures.

From picture tags, we then study the relationship between soundscapes and emotions. We learn that streets with music sounds are associated with strong emotions of joy or sadness, while those with human sounds are associated with joy or surprise.

Project Page: Chatty Maps

Media:

7. hitchBOT: Attitudes Towards a Canadian Hitchhiking Robot

Year: 2018

Paper with Kathleen Fraser, Frauke Zeller, David Smith, and Frank Rudzicz:

Quote:

In 2014, a chatty but immobile robot called hitchBOT set out to hitchhike across Canada. It similarly made its way across Germany and the Netherlands, and had begun a trip across the USA when it was destroyed by vandals. In this work, we analyze the emotions and sentiments associated with words in tweets posted before and after hitchBOT’s destruction to answer two questions: Were there any differences in the emotions expressed across the different countries visited by hitchBOT? And how did the public react to the demise of hitch-BOT?

8. Emotional Contagion

Year: 2018

in Fake News Distributed via Twitter
Paper by Soroush Vosoughi, Deb Roy, Sinan Aral:

“Whereas false stories inspired fear, disgust, and surprise in replies, true stories inspired anticipation, sadness, joy, and trust.”

in YouTube Vlogs
Paper by H. Rosenbusch, A.M. Evans, and M. Zeelenberg:

Quote:

The present analyses show two independent ways that emotions spread in the YouTube community. The first is an immediate emotion transfer that occurs when audience members watch a vlogger express emotions in a video. The second path is between average vlogger emotions (i.e., emotion averages over vlogs) and audience emotions, which materializes beyond the effect of the emotions in the vlog that is currently being watched. The two most popular interpretations of these two effects are emotional contagion for the immediate effect and similarity-based flocking (or homophily) for the sustained effect. Our analyses show that both effects, which were proposed in past psychological research, contribute independently to the apparent spread of emotions over social media. However, only the emotional contagion effect can really be labeled a spreading effect, as emotions are actually transferred from user to user. Homophily works the other way around by bringing users with similar emotions closer together. Thus, our models reveal that there is a spread of emotions as well as a “despread” (inching together) of similar users that lead to the observed correlations between the emotions of different people online.

Media:

9. How Emotions and Code Interact

Year: 2018

Analysis by Albert Ziegler:

Quotes:

Happiness leads to productivity and vice versa.
Sadness leads to cleaner code. Anger leads to mistakes.

In the minds of many (and in no small part thanks to Hollywood movies), developers work effortlessly, hands flying across the keyboard as they write code with ruthless efficiency while munching salty snacks. Programming is a very abstract, even foreign, concept to many, but the work that developers do matters; it leads to stronger and faster applications, better software and a safer online world. Within this context, we must remember that the coders behind the machines are not machines themselves. Like any person, a developer’s work is affected by their mood and well-being, which can have serious ramifications.

10. Sad Songs and Angry Characters

Years: 2017, 2018

Saddest of the Radiohead Songs: by Charlie Thompson in 2017

Quote:

Radiohead has been my favorite band for a while, so I am used to people politely suggesting that I play something “less depressing.” Much of Radiohead’s music is undeniably sad, and this post catalogs my journey to quantify that sadness, concluding in a data-driven determination of their most depressing song.

Media:

Emotional Characters on Seinfeld

Just got to know this sad news:

Turns out Frank Constanza was not the angriest on Seinfeld:
Analysis by Daniel Larson in 2018

Bonus Project: Word-Colour Associations

Years: 2011, 2020

Paper:

Quote:

Colour is a vital component in the successful delivery of information, whether it is in marketing a commercial product (Sable and Akcay, 2010), in webdesign (Meier, 1988; Pribadi et al., 1990), or in information visualization (Christ, 1975; Card et al.,1999). Since real-world concepts have associations with certain colour categories (for example,danger with red, and softness with pink), complementing linguistic and non-linguistic information with appropriate colours has a number of benefits.

We created a large word–colour association lexicon… We observed that abstract concepts, emotions in particular, have strong colour associations… We found that frequencies of colour choice in associations follow the same order in which colour terms occur in language (Berlin and Kay, 1969).

This data study was a last-minute addition to piggyback over the emotion lexicon study. #BerlinAndKayColorTerms #linguisticrelativity

LexiChrome an interactive catalogue for scholars, designers, and writers (built on top of the word-color association lexicon) with Chris Kim, Christopher Collins, and Uta Hinrichs.

Lexichrome
Lexichrome

Paper:

Lexichrome: Text Construction and Lexical Discovery with Word-Color Associations Using Interactive Visualization. Chris Kim, Uta Hinrichs, Saif M. Mohammad, and Christopher Collins. To appear in the Proceedings of DIS2020.

Feedback and Acknowledgments

We would love to hear your favorites and how you used the NRC Emotion Lexicon: uvgotsaif@gmail.com. You can find other research projects on my webpage.

Big thanks to everyone who has used the NRC Emotion Lexicon. Thanks to Peter Turney for being a great collaborator and source of inspiration. Thanks to Joel Martin for the support and encouragement to pursue work on the NRC Emotion Lexicon. Thanks also to the wonderful past and present colleagues at National Research Council Canada and the large vibrant community of Natural Language Processing researchers around the world for the thoughtful feedback and insightful suggestions.

Saif is Senior Research Scientist at the National Research Council Canada. His interests are in NLP, especially emotions, creativity, and fairness in language.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store