# When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis

arXiv: https://arxiv.org/abs/2106.00954 · HTML: https://mlsanity.com/paper/2106.00954/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 9 of 9)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://mlsanity.com/paper/1912.00741/) (2019)
- [Crowdsourcing a Word-Emotion Association Lexicon](https://mlsanity.com/paper/1308.6297/) (2013)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Interpretable & Explorable Approximations of Black Box Models](https://mlsanity.com/paper/1707.01154/) (2017)
- [Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure](https://mlsanity.com/paper/1809.07424/) (2018)
- [Sentiment of Emojis](https://mlsanity.com/paper/1509.07761/) (2015)

## Built on by (most cited first, 4 of 4)

- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods](https://mlsanity.com/paper/2511.15722/) (2025)
- [Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control](https://mlsanity.com/paper/2211.05750/) (2022)
- [Integrating Human-in-the-loop into Swarm Learning for Decentralized Fake News Detection](https://mlsanity.com/paper/2201.02048/) (2022)

## Abstract (arXiv)

Although deep neural networks have been widely employed and proven effective in sentiment analysis tasks, it remains challenging for model developers to assess their models for erroneous predictions that might exist prior to deployment. Once deployed, emergent errors can be hard to identify in prediction run-time and impossible to trace back to their sources. To address such gaps, in this paper we propose an error detection framework for sentiment analysis based on explainable features. We perform global-level feature validation with human-in-the-loop assessment, followed by an integration of global and local-level feature contribution analysis. Experimental results show that, given limited human-in-the-loop intervention, our method is able to identify erroneous model predictions on unseen data with high precision.