# Uncovering the Limits of Text-based Emotion Detection

arXiv: https://arxiv.org/abs/2109.01900 · HTML: https://mlsanity.com/paper/2109.01900/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 55 references that are in the map.
- First posted on arXiv 4 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances](https://mlsanity.com/paper/1905.02947/) (2019)
- [Survey on Emotional Body Gesture Recognition](https://mlsanity.com/paper/1801.07481/) (2018)
- [Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms](https://mlsanity.com/paper/1801.06482/) (2018)
- [NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets](https://mlsanity.com/paper/1308.6242/) (2013)
- [Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation](https://mlsanity.com/paper/1909.11974/) (2019)
- [SocialNLP EmotionX 2019 Challenge Overview: Predicting Emotions in Spoken Dialogues and Chats](https://mlsanity.com/paper/1909.07734/) (2019)
- [Sharing emotions at scale: The Vent dataset](https://mlsanity.com/paper/1901.04856/) (2019)
- [Deep Feelings: A Massive Cross-Lingual Study on the Relation between Emotions and Virality](https://mlsanity.com/paper/1503.04723/) (2015)

## Built on by (most cited first, 8 of 8)

- [StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series](https://mlsanity.com/paper/2301.09279/) (2023)
- [BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer](https://mlsanity.com/paper/2202.07543/) (2022)
- [Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification](https://mlsanity.com/paper/2504.16856/) (2025)
- [LEIA: Linguistic Embeddings for the Identification of Affect](https://mlsanity.com/paper/2304.10973/) (2023)
- [Sentiment is all you need to win US Presidential elections](https://mlsanity.com/paper/2209.13487/) (2022)
- [Guilt Detection in Text: A Step Towards Understanding Complex Emotions](https://mlsanity.com/paper/2303.03510/) (2023)
- [Leveraging the power of transformers for guilt detection in text](https://mlsanity.com/paper/2401.07414/) (2024)
- [SEER: The Span-based Emotion Evidence Retrieval Benchmark](https://mlsanity.com/paper/2510.03490/) (2025)

## Abstract (arXiv)

Identifying emotions from text is crucial for a variety of real world tasks. We consider the two largest now-available corpora for emotion classification: GoEmotions, with 58k messages labelled by readers, and Vent, with 33M writer-labelled messages. We design a benchmark and evaluate several feature spaces and learning algorithms, including two simple yet novel models on top of BERT that outperform previous strong baselines on GoEmotions. Through an experiment with human participants, we also analyze the differences between how writers express emotions and how readers perceive them. Our results suggest that emotions expressed by writers are harder to identify than emotions that readers perceive. We share a public web interface for researchers to explore our models.