| November 18, 2009
The purpose of this paper is to present a methodology for constructing market sentiment indices based on news sentiment.
The market sentiment indices are to be considered a first step in creating a range of company sentiment indices, which take into consideration not only company specific news events, but also broader market sentiment.
One way of constructing market sentiment indices is to consider ratios of positive and negative sentiment counts over well-defined backward-looking news sentiment aggregation windows.
The resulting indices can be used either as quant factors in multi-factor models or as part of creating triggering events applied in high frequency trading or longer-term investing.
Specifically, applying the "optimal" news sentiment aggregation window as part of a DJIA sentiment index, we arrive at correlations between the sentiment index values and the two week forward-looking returns that range between 20 - 27%, while for a Eurostoxx50 sentiment index the corresponding range is 9-â€“ 15%. Furthermore, we find Hit ratios ranging between 59 - 65% and 55 - 67% for the DJIA and Eurostoxx sentiment indices, respectively; this with Profit/Loss ratios ranging between 1.01 - 1.27 and 0.86 - 1.18.
Although there is no single definition of investor sentiment, according to Johnson et.al.  most discussions involve (a) investors optimism or pessimism about stocks, (b) beliefs not justified by fundamentals, or (c) mis-evaluation by some investors. Since investor sentiment is not directly observable, researchers have employed various measures of sentiment. Proxies include the closed-end fund discount, mutual fund redemptions, the volume of initial public offerings, ratio of odd-lot sales to purchases, consumer and investor survey data, technical indicators, and the proportion of fund assets held in cash.
In addition to these sentiment proxies, a range of economic indicators are available of which some are considered part of different governments official list of leading indicators. The indicators that make reference to sentiment, are mainly generated from surveys and address consumer sentiment. The release schedule for these indicators are often either monthly or quarterly, making them less timely than the news sentiment indices suggested in this paper. News sentiment indices are more timely because they are continuously calculated in a consistent manner from real-time media coverage. In the U.S., examples of sentiment-based economic indicators include the Conference Board Consumer Confidence Index, the University of Michigan Consumer Sentiment Index, and the Washington-ABC News Consumer Comfort Index. While in Europe, examples include the German IFO Business Climate Index, and the French Business Sentiment Index. All of the mentioned proxies and indicators try to capture market-wide sentiment rather than sentiment at the individual company level. We propose using news sentiment in order to capture not only market-wide sentiment focussing on specific indices, but also to use news sentiment to construct company level sentiment indices.
According to the Capital Asset Pricing Model (CAPM), stock price innovations can be explained by two main risk components including market risk and idiosyncratic risk. Assuming that news entries about individual companies can be considered proxies for the idiosyncratic risk component, and that the aggregate news entries for all companies belonging to a particular sector or index act as proxies for the market risk component, it is possible to construct company sentiment indices combining these two signals. In this paper, we describe the methodology for how to construct one of the two components namely the market sentiment index. The objective of creating a sentiment index is to capture the potential longer-term effects of news sentiment on market or individual stock prices. In essence, the idiosyncratic sentiment index should help explain the movements in abnormal or excess stock returns, while the market sentiment index should ideally help explain the overall market movements. Letting Rmt represent the market return and Rf t the riskless rate, the CAPM is given by...
Please use your business email. If you don't have one, please email us at firstname.lastname@example.org.
We will process your personal data with the purpose of managing your personal account on
RavenPack and offering our services. You can exercise your rights of access, rectification,
erasure, restriction of processing, data portability and objection by emailing us at email@example.com. For more information, you can
Your request has been recorded and a team member will be in touch soon.
We consider incorporating sentiment signals from news, earnings call transcripts, and insider transactions to
boost the risk-adjusted returns, and revive factor performance.
We find stronger, more predictable market reactions when the words of company executives agree with their actions.
We have gathered 12 insights from 2021 research that can be leveraged in 2022.