The Financial News index (FNI) is designed to track Norwegian GDP growth and the business cycle at high frequency. Its underlying indicators, and novelty, are daily time series representing how much the media writes about various topics.
The central idea behind the index is simple: To the extent that newspapers provide a relevant description of the economy, the more intensive a given topic is represented in the newspaper at a given point in time, the more likely it is that this topic represents something of importance for the economy's current and future needs and developments.
Thus, the FNI index captures the continuously evolving narrative about economic conditions, and relates this to actual GDP growth and the business cycle.
The average value of the FNI index is zero. Progressively bigger positive values indicate progressively better-than-average business cycle conditions. Conversely, progressively more negative values indicate progressively worse-than-average conditions.
Disclaimer: All opinions and estimates of the FNI are, regardless of source, given in good faith. The user assumes the entire risk related to the use of this information. The authors are providing this information ”as is,” and the authors disclaim any and all warranties of merchantability or fitness for a particular purpose. In no event will the authors be liable for any damages or lost profit resulting from any use or misuse of this information.
Decision makers and forecasters need to assess the state of the economy in real time to devise appropriate policy responses and condition on an updated information set. However, in real time, our main measure of economic activity, GDP growth, is not observed as it is compiled on a quarterly frequency and published with a considerable lag, usually up to at least one quarter.
Internationally, many high frequency business cycle indicators have been constructed to mediate these caveats. For the Norwegian economy, no such high frequency indicators exist. The FNI aims to fill this hole. However, unlike other (international) indexes with the same purpose, it has one distinctive property: The information set used to derive the index consists of daily newspaper topics.
The FNI published here utilizes a large newspaper corpus from many different news sources. In short, this combined corpus is first decomposed into distinct daily news topics. In turn, these news topics are used together with Gross Domestic Product (GDP) to derive the daily index. The construction of the FNI is based on the framework developed in Leif Anders Thorsrud (2016), "Words are the new numbers: A newsy coincident index of business cycles," Working Papers 4/2016, Centre for Applied Macro- and Petroleum economics (CAMP), BI Norwegian Business School. In this research article it is shown that the derived index has very good classification properties for the Norwegian business cycle. That is, it captures expansions and recessions well. We refer to this article for an in-debt description of how the index is constructed.
This is the start of an ongoing research cooperation to enhance knowledge on macroeconomic developments.
The construction of the FNI is part of a larger research agenda where unstructured textual data is used to understand and explain (macro) economic fluctuations. The interested reader can find related literature here:
The media landscape is one constant flow of information. Retriever help you keep tabs on all media mentioning’s derived from editorial and social media. For almost 20 years, we have listened to, monitored, measured and analyzed the world of media, breaking down complex data into clear information.
CAMP is a research center located at BI Norwegian Business School. The center's objectives are to advance research and post-graduate training in relevant fields. The center will conduct original and objective research to improve the understanding of macroeconomic issues of resource rich economies, and to act as a forum for discussion of policy issues between academia, government and the private sector. CAMP is headed by Professor Hilde C. Bjørnland.