Economics blogs sentiment and asset prices

• Author: Antonio Parisi,Ugo Pomante,Vincenzo Farina
• Date: 01 October 2017
• DOI: http://doi.org/10.1002/ijfe.1591
• Published date: 01 October 2017

RESEARCH ARTICLE

Economics blogs sentiment and asset prices

†

Vincenzo Farina | Antonio Parisi | Ugo Pomante

University of Rome Tor Vergata, Via

Columbia 2, 00133 Rome, Italy

Correspondence

Vincenzo Farina, University of Rome Tor

Vergata, Via Columbia 2, 00133 Rome,

Italy.

Email: vincenzo.farina@uniroma2.it

JEL Classification: E32; G12; G14

Abstract

One of the most important research streams in finance is to understand the

determinants of stock market dynamics. Using a large amount of linguistic data

regarding 960,808 posts during a 5‐year time period (from March 1, 2008, to

August 31, 2013), we develop an economics blogs pessimism indicator (consid-

ered as a proxy for either investor sentiment or risk aversion), and we show its

validity to build performing trading strategies.

KEYWORDS

economics blogs,investor sentiment, NLP text analysis, stock market, trading strategies

1|INTRODUCTION

One of the most important research streams in finance

aims at understanding the determinants of stock market

dynamics. According to the theory of efficient financial

markets (Fama, 1970), stock prices should reflect all avail-

able information. However, the evidence of autocorrela-

tion of stock returns in the short term (Hong, Touros, &

Valkanov, 2007; Jegadeesh & Titman, 1993; Moskowitz

& Grinblatt, 1999) suggests that stock prices do not fully

adjust to new information.

Market sentiment does not play any role in the classic

approach to finance. On the contrary, the behavioural

approach suggests that waves of irrational sentiment, that

is, times of overly optimistic or pessimistic expectations,

can persist and affect asset prices for significant periods

of time (Baker & Wurgler, 2006; De Long, Shleifer, Sum-

mers, & Waldmann, 1990).

This view posits the existence of two types of traders,

noise traders who hold random beliefs about future divi-

dends and rational arbitrageurs who hold Bayesian

beliefs. The level of noise traders'beliefs relative to Bayes-

ian beliefs could be referred as investor sentiment. When

noise traders have expectations of future dividends that

are below/above the expectations of rational arbitrageurs,

we are in presence of a pessimistic/optimistic sentiment.

Lee, Shleifer, and Thaler (1991) first investigate the

empirical implications of this theory by assuming that

noise traders are individual investors.

In general, models of investor sentiment predict that

low sentiment will generate downward price pressure

and unusually high or low values of sentiment will pro-

duce high volume. However, models of trade for any

noninformational reason, such as liquidity needs or sud-

den changes in risk aversion (Campbell, Grossman, &

Wang, 1993), make these same predictions. In detail,

Campbell et al. (1993) find that returns accompanied by

high volume tend to be reversed more strongly, and they

explain that the result is consistent with a model in which

some investors are compensated for accommodating the

liquidity demands of others.

According to Tetlock (2007), the only way to distin-

guish noise trader and liquidity trader theories is to inter-

pret the media pessimism variable as a proxy for either

investor sentiment or risk aversion.

Mass media represent a fundamental tool in the pro-

duction and the widespread of the information, and it is

still debated whether they induce, amplify, or simply

reflect investors'interpretations of stock market

†

The authors wish to thank the participants at the 2014 Annual Meeting

of the European Financial Management Association (EFMA) and the

participants at the 2014 Annual Meeting of the Italian Association of

Scholars of Economics and Management of Financial Institutions and

Markets (ADEIMF) for their very helpful comments. All errors, of

course, rest with the authors.

Received: 13 January 2016 Revised: 3 August 2017 Accepted: 16 September 2017

DOI: 10.1002/ijfe.1591

Int J Fin Econ. 2017;22:341–351. Copyright © 2017 John Wiley & Sons, Ltd.wileyonlinelibrary.com/journal/ijfe 341