“This is a timely—and exciting—book. The technology of extracting financial sentiment from news feeds and other such sources is one that has been slowly growing, supported by the accelerating infrastructure provided by the world wide web. Over the past ten years or so, papers have been appearing showing that useful information can be extracted in this way. Moreover, one can legitimately expect the rate of progress to gather pace, as other supporting web technologies continue to develop.
This book is the first to provide a comprehensive overview of the state of the art. It will attract a lot of attention. From a technical perspective, the area presents some deep and interesting challenges, which are nicely captured here. One is the central issue of fusing entirely different kinds of information, from quite distinct sources, and with very different degrees of reliability. Another is an issue which mining of large observational data sets has to contend with, whatever its area of application, namely the problem of selection bias: it is all too easy to extract a distorted, non-representative data set, so that any analyses based on it are at risk of mistaken conclusions. Overall, this technology is still in its infancy, but the papers presented in this volume provide a perfect launch pad for the future of news analytics in finance.
Just as social statistics enables us both to define and ...
Get The Handbook of News Analytics in Finance now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
