Much of the world's data is textual - in large document archives, in scientific papers, in scattered websites, in social media. The information contained in text is invaluable and yet hard to access. The sheer volume of text means that, unassisted, we cannot hope to read all available sources,...

Motivated by incongruences between today’s complex data, problems and requirements and available methodological frameworks, we propose data quilting as a means of combining and presenting the analysis of multiple types of data to create a single cohesive deliverable. We introduce data quilting...

Text data is ultra-high dimensional, which makes machine learning techniques indispensable for textual analysis. Text is often selected—journalists, speechwriters, and others craft messages to target their audiences' limited attention. We develop an economically motivated high dimensional...

Text data is ultra-high dimensional, which makes machine learning techniques indispensable for textual analysis. Text is often selected—journalists, speechwriters, and others craft messages to target their audiences' limited attention. We develop an economically motivated high dimensional...

We propose a novel approach to measure monetary policy shocks using sentiment analy-\sis, which is relatively free from specification errors compared to VAR-identified shocks and allows time for a wider circle of market participants to digest information com-pared to shocks identified through...

This paper reviews the accounting literature that studied readability of corporate narrative disclosures as a dependent variable being affected by firm performance, desire to highlight good news or hide bad news, risk exposures, among others, or as an independent variable affecting decision...

Text data is ultra-high dimensional, which makes machine learning techniques indispensable for textual analysis. Text is often selected--journalists, speechwriters, and others craft messages to target their audiences' limited attention. We develop an economically motivated high dimensional...

We introduce a general framework for analyzing large-scale text-based data, combining the strengths of neural-network language processing and generative statistical modeling. Our methodology generates textual factors by (i) representing texts using vector word embedding, (ii) clustering words...

This study examines the applicability of modern Data Science techniques in the domain of Strategy. We apply novel techniques from the field of machine learning and text analysis. WE proceed in two steps. First, we compare different machine learning techniques to traditional regression methods in...

Using a multi-stage filtering procedure based on both algorithms and human judgement, we develop a Chinese Financial Sentiment Dictionary (CFSD) with the hope to help advance textual analysis of Chinese documents in accounting and finance. There are 1,489 negative words and 1,108 positive words...