# Training and Prediction Data Discrepancies: Challenges of Text Classification with Noisy, Historical Data

arXiv: https://arxiv.org/abs/1809.04019 · HTML: https://mlsanity.com/paper/1809.04019/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2018.

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

- [On Sensitivity of Deep Learning Based Text Classification Algorithms to Practical Input Perturbations](https://mlsanity.com/paper/2201.00318/) (2022)
- [A Fast Randomized Algorithm for Massive Text Normalization](https://mlsanity.com/paper/2110.03024/) (2021)
- [Automated Trustworthiness Testing for Machine Learning Classifiers](https://mlsanity.com/paper/2406.05251/) (2024)
- [Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs](https://mlsanity.com/paper/2604.12049/) (2026)
- [Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)](https://mlsanity.com/paper/2604.15547/) (2026)

## Abstract (arXiv)

Industry datasets used for text classification are rarely created for that purpose. In most cases, the data and target predictions are a by-product of accumulated historical data, typically fraught with noise, present in both the text-based document, as well as in the targeted labels. In this work, we address the question of how well performance metrics computed on noisy, historical data reflect the performance on the intended future machine learning model input. The results demonstrate the utility of dirty training datasets used to build prediction models for cleaner (and different) prediction inputs.