# Empath: Understanding Topic Signals in Large-Scale Text

arXiv: https://arxiv.org/abs/1602.06979 · HTML: https://mlsanity.com/paper/1602.06979/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2016.

## Built on by (most cited first, 30 of 51)

- [HateMM: A Multi-Modal Dataset for Hate Video Classification](https://mlsanity.com/paper/2305.03915/) (2023)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [Uncovering Implicit Gender Bias in Narratives through Commonsense Inference](https://mlsanity.com/paper/2109.06437/) (2021)
- [Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources](https://mlsanity.com/paper/2103.11320/) (2021)
- [Emotion Detection for Misinformation: A Review](https://mlsanity.com/paper/2311.00671/) (2023)
- [BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification](https://mlsanity.com/paper/2310.11748/) (2023)
- [Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use](https://mlsanity.com/paper/2410.19155/) (2024)
- ["Short is the Road that Leads from Fear to Hate": Fear Speech in Indian WhatsApp Groups](https://mlsanity.com/paper/2102.03870/) (2021)
- [Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Science](https://mlsanity.com/paper/2203.07031/) (2022)
- [To Protect and To Serve? Analyzing Entity-Centric Framing of Police Violence](https://mlsanity.com/paper/2109.05325/) (2021)
- [Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis](https://mlsanity.com/paper/2410.03908/) (2024)
- [FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning](https://mlsanity.com/paper/2310.16538/) (2023)
- [Optimizing Language Models for Human Preferences is a Causal Inference Problem](https://mlsanity.com/paper/2402.14979/) (2024)
- [The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories](https://mlsanity.com/paper/2406.16767/) (2024)
- [PVG at WASSA 2021: A Multi-Input, Multi-Task, Transformer-Based Architecture for Empathy and Distress Prediction](https://mlsanity.com/paper/2103.03296/) (2021)
- [Computational Turing Test Reveals Systematic Differences Between Human and AI Language](https://mlsanity.com/paper/2511.04195/) (2025)
- [Heterogeneous Peer Effects in the Linear Threshold Model](https://mlsanity.com/paper/2201.11242/) (2022)
- [Understanding the Role of Affect Dimensions in Detecting Emotions from Tweets: A Multi-task Approach](https://mlsanity.com/paper/2105.03983/) (2021)
- [Explaining Outcomes of Multi-Party Dialogues using Causal Learning](https://mlsanity.com/paper/2105.00944/) (2021)
- [Detecting Pump&Dump Stock Market Manipulation from Online Forums](https://mlsanity.com/paper/2301.11403/) (2023)
- [Revealing Temporal Label Noise in Multimodal Hateful Video Classification](https://mlsanity.com/paper/2508.04900/) (2025)
- [United States Politicians' Tone Became More Negative with 2016 Primary Campaigns](https://mlsanity.com/paper/2207.08112/) (2022)
- [SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations](https://mlsanity.com/paper/2305.14728/) (2023)
- [Othering and low status framing of immigrant cuisines in US restaurant reviews and large language models](https://mlsanity.com/paper/2307.07645/) (2023)
- [Inclusivity in Large Language Models: Personality Traits and Gender Bias in Scientific Abstracts](https://mlsanity.com/paper/2406.19497/) (2024)
- [Isolated Causal Effects of Natural Language](https://mlsanity.com/paper/2410.14812/) (2024)
- [Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations](https://mlsanity.com/paper/2505.08348/) (2025)
- [Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data](https://mlsanity.com/paper/2201.10986/) (2022)
- [Mental Disorders on Online Social Media Through the Lens of Language and Behaviour: Analysis and Visualisation](https://mlsanity.com/paper/2202.03291/) (2022)
- [Dictionary-Assisted Supervised Contrastive Learning](https://mlsanity.com/paper/2210.15172/) (2022)

## Abstract (arXiv)

Human language is colored by a broad range of topics, but existing text analysis tools only focus on a small number of them. We present Empath, a tool that can generate and validate new lexical categories on demand from a small set of seed terms (like "bleed" and "punch" to generate the category violence). Empath draws connotations between words and phrases by deep learning a neural embedding across more than 1.8 billion words of modern fiction. Given a small set of seed words that characterize a category, Empath uses its neural embedding to discover new related terms, then validates the category with a crowd-powered filter. Empath also analyzes text across 200 built-in, pre-validated categories we have generated from common topics in our web dataset, like neglect, government, and social media. We show that Empath's data-driven, human validated categories are highly correlated (r=0.906) with similar categories in LIWC.