# Guilt by Association: Emotion Intensities in Lexical Representations

arXiv: https://arxiv.org/abs/2104.08679 · HTML: https://mlsanity.com/paper/2104.08679/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [Word Affect Intensities](https://mlsanity.com/paper/1704.08798/) (2017)
- [WASSA-2017 Shared Task on Emotion Intensity](https://mlsanity.com/paper/1708.03700/) (2017)
- [Practical and Ethical Considerations in the Effective use of Emotion and Sentiment Lexicons](https://mlsanity.com/paper/2011.03492/) (2020)
- [DepecheMood: a Lexicon for Emotion Analysis from Crowd-Annotated News](https://mlsanity.com/paper/1405.1605/) (2014)
- [DepecheMood++: a Bilingual Emotion Lexicon Built Through Simple Yet Powerful Techniques](https://mlsanity.com/paper/1810.03660/) (2018)
- [Ultradense Word Embeddings by Orthogonal Transformation](https://mlsanity.com/paper/1602.07572/) (2016)
- [Emotion Representation Mapping for Automatic Lexicon Construction (Mostly) Performs on Human Level](https://mlsanity.com/paper/1806.08890/) (2018)
- [Aff2Vec: Affect--Enriched Distributional Word Representations](https://mlsanity.com/paper/1805.07966/) (2018)
- [Learning Emotion from 100 Observations: Unexpected Robustness of Deep Learning under Strong Data Limitations](https://mlsanity.com/paper/1810.10949/) (2018)

## Abstract (arXiv)

What do word vector representations reveal about the emotions associated with words? In this study, we consider the task of estimating word-level emotion intensity scores for specific emotions, exploring unsupervised, supervised, and finally a self-supervised method of extracting emotional associations from word vector representations. Overall, we find that word vectors carry substantial potential for inducing fine-grained emotion intensity scores, showing a far higher correlation with human ground truth ratings than achieved by state-of-the-art emotion lexicons.