Constructing a Sentiment Factor

RavenPack | February 01, 2012

This document describes the methodology behind the construction of the RavenPack Sentiment Factor

The RavenPack Sentiment Factor, which is based on a stocks' exposure to changes in overall market sentiment as measured by the RavenPack Sentiment Index (US).

Calculating the RavenPack Sentiment Index

The RavenPack Sentiment Index is the 90 day simple moving average of the difference between the count of positive and negative news about stocks as measured by the RavenPack Event Sentiment Score.

Measuring News Beta

A stock’s exposure (aka news beta) to the change in overall market sentiment is estimated as the coefficient in the timeseries regression of individual stock returns on changes in the RavenPack Sentiment Index after controlling for traditional risk factors such as market, size, value, and momentum.

Calculating the RavenPack Sentiment Factor

The RavenPack Sentiment Factor is calculated as the difference between the average value-weighted return on the two low news beta portfolios (small or large) and the average valueweighted return on the two high news beta portfolios (small or large)

Introduction

Market sentiment has been found to affect the time series of asset returns as well as in the cross-section. Specifically Baker and Wurgler (2006) find that when sentiment is low, the average future returns of speculative stocks exceed those of bond-like stocks. When sentiment is high, the average future returns of speculative stocks are on average lower than the returns of bond-like stocks.

Using the RavenPack Sentiment Index derived from the RavenPack News Analytics dataset, we’ve also found evidence supporting the return predictability from stocks’ exposure to market sentiment (for details, please refer to “Factoring Sentiment Risk into Quant Models”).

This evidence suggests that exposure to market sentiment is an untapped source of alpha in financial markets. To verify that sentiment risk is a general risk factor important to asset pricing, we construct a sentiment factor based on individual stock exposures to market sentiment in a way similar to the construction of traditional factors like momentum or reversal.

The rest of the paper will describe the construction methodology in details.



By providing your personal information and submitting your details, you acknowledge that you have read, understood, and agreed to our Privacy Statement and you accept our Terms and Conditions. We will handle your personal information in compliance with our Privacy Statement. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability, and objection by emailing us at privacy@ravenpack.com in accordance with the GDPRs. You also are agreeing to receive occasional updates and communications from RavenPack about resources, events, products, or services that may be of interest to you.

Data Insights

Read More