# Data Augmentation for Improving Emotion Recognition in Software Engineering Communication

arXiv: https://arxiv.org/abs/2208.05573 · HTML: https://mlsanity.com/paper/2208.05573/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2022.

## Built on by (most cited first, 5 of 5)

- [What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants](https://mlsanity.com/paper/2605.30777/) (2026)
- [Data Augmentation for Emotion Detection in Small Imbalanced Text Data](https://mlsanity.com/paper/2310.17015/) (2023)
- [LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2603.01778/) (2026)
- [Sentiment analysis for software engineering: How far can zero-shot learning (ZSL) go?](https://mlsanity.com/paper/2604.13826/) (2026)
- [Fine-Grained Emotion Classification from Mobile App Reviews: An Empirical Study with Large Language Models](https://mlsanity.com/paper/2610.03802/) (2026)

## Abstract (arXiv)

Emotions (e.g., Joy, Anger) are prevalent in daily software engineering (SE) activities, and are known to be significant indicators of work productivity (e.g., bug fixing efficiency). Recent studies have shown that directly applying general purpose emotion classification tools to SE corpora is not effective. Even within the SE domain, tool performance degrades significantly when trained on one communication channel and evaluated on another (e.g, StackOverflow vs. GitHub comments). Retraining a tool with channel-specific data takes significant effort since manually annotating large datasets of ground truth data is expensive. In this paper, we address this data scarcity problem by automatically creating new training data using a data augmentation technique. Based on an analysis of the types of errors made by popular SE-specific emotion recognition tools, we specifically target our data augmentation strategy in order to improve the performance of emotion recognition. Our results show an average improvement of 9.3% in micro F1-Score for three existing emotion classification tools (ESEM-E, EMTk, SEntiMoji) when trained with our best augmentation strategy.