Paper: arXiv 2506.06329
Authors: Zheng Cao, Wanchaloem Wunkaew, Helyette Geman
Abstract
This paper introduces the Hype Index as a novel metric to quantify media attention toward large-cap equities, leveraging advances in Natural Language Processing (NLP) for extracting predictive signals from financial news. Using the S&P 100 as the focus universe, we first construct a News Count-Based Hype Index, which measures relative media exposure by computing the share of news articles referencing each stock or sector. We then extend it to the Capitalization Adjusted Hype Index, adjusts for economic size by taking the ratio of a stock’s or sector’s media weight to its market capitalization weight within its industry or sector. We compute both versions of the Hype Index at the stock and sector levels, and evaluate them through multiple lenses: (1) their classification into different hype groups, (2) their associations with returns, volatility, and VIX index at various lags, (3) their signaling power for short-term market movements, and (4) their empirical properties including correlations, samplings, and trends. Our findings suggest that the Hype Index family provides a valuable set of tools for stock volatility analysis, market signaling, and NLP extensions in Finance.
Complexity vs Empirical Score
- Math Complexity: 4.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The math is relatively straightforward, relying on basic ratios and simple statistical measures like correlations and lag analysis rather than advanced theorems, while the empirical work is substantial, featuring detailed data collection from Refinitiv, backtesting on S&P 100 with 326 days of news, and multiple hypothesis tests across returns, volatility, and VIX.
Research Flowchart
flowchart TD
A["Research Goal<br>Determine the predictive value of<br>NLP-based Media Attention"] --> B["Data Collection<br>S&P 100 Stocks &<br>Financial News Articles"]
B --> C["Key Methodology<br>NLP Processing &<br>Media Count Analysis"]
C --> D{"Computation"}
D --> E["News Count-Based Hype Index<br>Relative Media Exposure"]
D --> F["Capitalization Adjusted Hype Index<br>Media Weight / Mkt Cap Weight"]
E --> G["Analysis & Evaluation"]
F --> G
G --> H["Key Outcomes<br>Volatility Analysis<br>Market Signaling<br>NLP Finance Extension"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes the Hype Index, a novel metric to quantify media attention toward large‑cap equities using NLP, with both a news count‑based version and a capitalization‑adjusted version.
Source sentence
This paper introduces the Hype Index as a novel metric to quantify media attention toward large-cap equities, leveraging advances in Natural Language Processing (NLP) for extracting predictive signals from financial news.
Assumes 2
- The analysis is limited to the constituents of the S&P 100 index as of March 18 2024. data
Source sentence
Our analysis focuses on the constituents of the S&P 100 index as of March 18, 2024.
- News articles are reliably matched to firms using Refinitiv’s entity recognition filtering. data
Source sentence
Refinitiv’s entity recognition feature allows preliminary filtering to ensure that news articles are reliably associated with the correct companies.
Data
- LSEG news headlines text-news commercial
Source sentence
We collected financial news data from LSEG Data & Analytics, formerly Refinitiv, covering the period from December 21, 2023 to April 10, 2025, a total of 326 Business trading days.
- Daily market capitalization data fundamentals commercial
Source sentence
Daily market capitalization data for each company was collected from Refinitiv Workspace, aligned with the news data on a daily basis.
Costs
Not applicable
Finds 3
- The Hype Index family is found to be useful for stock volatility analysis and market signaling. statistical
Source sentence
Our findings suggest that the Hype Index family provides a valuable set of tools for stock volatility analysis, market signaling, and NLP extensions in Finance.
- The capitalization‑adjusted Hype Index does not follow a normal distribution according to multiple tests. statistical
Source sentence
All tests indicate a statistically significant deviation from normality. Therefore, the capitalization-adjusted Hype Index is not well-modeled by a normal
- A power‑law fit between news coverage and market cap explains slightly more variance (R² = 0.631) than a linear fit (R² = 0.614). statistical
Source sentence
Linear Fit: y = 1.19x −0.02, R2 = 0.614 Power Fit: y = 2.28x1.41, R2 = 0.631
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 18 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (41)
- A sentiment analysis approach to the prediction of market volatility (2022) — link
- The Pricing of Options and Corporate Liabilities (1973) — link
- Master’s Thesis: The Hyped-Adjusted Probability Measure (2025)
- LSEG Data and Analytics (2024) — link
- Introduction to News Sentiment Analysis with Eikon Data APIs - a Python example (2024) — link
- Linear Discriminant Analysis: A Brief Tutorial (1998) — link
- Financial News Data (2022) — link
- Financial Reports SEC (2022) — link
and 33 more
- EDGAR Crawler (2022) — link
- Financial News Headlines (2022) — link
- Monte Carlo Methods in Financial Engineering (2004)
- A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options (1993)
- Arbitrage-Free SVI Volatility Surfaces (2014)
- Honors Senior Thesis: Stochastic Calculus for Option Pricing with Convex Duality, Logistic Model, & Numerical Examination — → 2408.05672
- Theoretical and Empirical Validation of Heston Model — → 2409.12453
- Convex Duality in Continuous Option Pricing Models (2024) — link
- Martingales and arbitrage in multiperiod securities markets (1979) — link
- The Theory of Speculation (1900) — link
- Changes of Num' e raire, Changes of Probability Measure and Option Pricing (1995) — link
- Sentiment Analysis and Opinion Mining (2012) — link
- The Role of Sentiment in Financial Markets: A Survey of the Theoretical and Empirical Literature (2001) — link
- Sentiment, Trading Behavior, and Investors’ Decision-Making (2018) — link
- Sentiment-Guided Adversarial Learning for Stock Price Prediction (2023)
- New News is Bad News — → 2309.05560
- A Neural Probabilistic Language Model (2003)
- Twitter sentiment around the earnings announcement events (2016) — link
- Does Unusual News Forecast Market Stress? (2017) — link
- A Hype-Adjusted Probability Measure for NLP Stock Return Forecasting — → 2412.07587
- Driven to Distraction: Extraneous Events and Underreaction to Earnings News (2009) — link
- Investor Sentiment and the Cross-Section of Stock Returns (2006) — link
- VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text (2014) — link
- Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition (2000)
- Helyette Geman’s Professional Website (2025) — link
- Hype Index, Neutrality, and Momentum for Stocks (2025)
- Volatility Index Methodology: Cboe Volatility Index (VIX) (2024)
- Measuring Geopolitical Risk (2022) — link
- Attention is All You Need (2017)
- Giving Content to Investor Sentiment: The Role of Media in the Stock Market (2007) — link
- Does Unusual News Forecast Market Stress? (2019) — link
- Giving Content to Investor Sentiment: The Role of Media in the Stock Market (Forthcoming)
- Does the Stock Market Overreact? (1985) — link
4 of 41 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.