# Keystroke dynamics as signal for shallow syntactic parsing

arXiv: https://arxiv.org/abs/1610.03321 · HTML: https://mlsanity.com/paper/1610.03321/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2016.

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

- [Synthesizing Human Gaze Feedback for Improved NLP Performance](https://mlsanity.com/paper/2302.05721/) (2023)
- [Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior](https://mlsanity.com/paper/2309.00359/) (2023)
- [Learning Syntax from Naturally-Occurring Bracketings](https://mlsanity.com/paper/2104.13933/) (2021)
- [LLM-Assisted Cheating Detection in Korean Language via Keystrokes](https://mlsanity.com/paper/2507.22956/) (2025)
- [Teaching Human Behavior Improves Content Understanding Abilities Of LLMs](https://mlsanity.com/paper/2405.00942/) (2024)
- [Detecting Cognitive Signatures in Typing Behavior for Non-Intrusive Authorship Verification](https://mlsanity.com/paper/2603.00177/) (2026)
- [TypeShift: A User Interface for Visualizing the Typing Production Process](https://mlsanity.com/paper/2103.04222/) (2021)
- [ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues](https://mlsanity.com/paper/2607.01242/) (2026)

## Abstract (arXiv)

Keystroke dynamics have been extensively used in psycholinguistic and writing research to gain insights into cognitive processing. But do keystroke logs contain actual signal that can be used to learn better natural language processing models? We postulate that keystroke dynamics contain information about syntactic structure that can inform shallow syntactic parsing. To test this hypothesis, we explore labels derived from keystroke logs as auxiliary task in a multi-task bidirectional Long Short-Term Memory (bi-LSTM). Our results show promising results on two shallow syntactic parsing tasks, chunking and CCG supertagging. Our model is simple, has the advantage that data can come from distinct sources, and produces models that are significantly better than models trained on the text annotations alone.