Textual Analysis in Accounting and Finance: A Survey
TL;DR: This survey describes the nuances of the method and, as users of textual analysis, some of the tripwires in implementation and reviews the contemporary textual analysis literature to highlight areas of future research.
Abstract: Relative to quantitative methods traditionally used in accounting and finance, textual analysis is substantially less precise Thus, understanding the art is of equal importance to understanding the science In this survey we describe the nuances of the method and, as users of textual analysis, some of the tripwires in implementation We also review the contemporary textual analysis literature and highlight areas of future research
Citations
More filters
TL;DR: The authors discusses the empirical literature on the economic consequences of disclosure and financial reporting regulation, drawing on U.S. and international evidence, highlighting the challenges with quantifying regulatory costs and benefits, measuring disclosure and reporting outcomes, and drawing causal inferences from regulatory studies.
Abstract: This paper discusses the empirical literature on the economic consequences of disclosure and financial reporting regulation, drawing on U.S. and international evidence. Given the policy relevance of research on regulation, we highlight the challenges with (1) quantifying regulatory costs and benefits, (2) measuring disclosure and reporting outcomes, and (3) drawing causal inferences from regulatory studies. Next, we discuss empirical studies that link disclosure and reporting activities to firm-specific and market-wide economic outcomes. Understanding these links is important when evaluating regulation. We then synthesize the empirical evidence on the economic effects of disclosure regulation and reporting standards, including the evidence on International Financial Reporting Standards (IFRS) adoption. Several important conclusions emerge. We generally lack evidence on market-wide effects and externalities from regulation, yet such evidence is central to the economic justification of regulation. Moreover, evidence on causal effects of disclosure and reporting regulation is still relatively rare. We also lack evidence on the real effects of such regulation. These limitations provide many research opportunities. We conclude with several specific suggestions for future research.
779 citations
TL;DR: The authors discusses the empirical literature on the economic consequences of disclosure and financial reporting regulation (including IFRS adoption), drawing on U.S. and international evidence, highlighting the challenges with quantifying regulatory costs and benefits, measuring disclosure and reporting outcomes, and drawing causal inferences from regulatory studies.
Abstract: This paper discusses the empirical literature on the economic consequences of disclosure and financial reporting regulation (including IFRS adoption), drawing on U.S. and international evidence. Given the policy relevance of research on regulation, we highlight the challenges with: (i) quantifying regulatory costs and benefits, (ii) measuring disclosure and reporting outcomes, and (iii) drawing causal inferences from regulatory studies. Next, we discuss empirical studies that link disclosure and reporting activities to firm-specific and market-wide economic outcomes. Understanding these links is important when evaluating regulation. We then synthesize the empirical evidence on the economic effects of disclosure regulation and reporting standards, including the evidence on IFRS adoption. Several important conclusions emerge. We generally lack evidence on market-wide effects and externalities from regulation, yet such evidence is central to the economic justification of regulation. Moreover, evidence on causal effects of disclosure and reporting regulation is still relatively rare. We also lack evidence on the real effects of such regulation. These limitations provide many research opportunities. We conclude with several specific suggestions for future research.
537 citations
Cites methods from "Textual Analysis in Accounting and ..."
...By aggregating across measures, these studies attempt to obtain a less specific (or summary) measure 19 See also Das (2014) and Loughran and McDonald (2014, 2016)....
[...]
401 citations
TL;DR: The authors found that words are part of almost every marketplace interaction, including online reviews, customer service calls, press releases, marketing communications, and other interactions create a wealth of textual data.
Abstract: Words are part of almost every marketplace interaction. Online reviews, customer service calls, press releases, marketing communications, and other interactions create a wealth of textual data. But...
321 citations
References
More filters
Proceedings Article•
03 Jan 2001TL;DR: This paper proposed a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI).
Abstract: We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.
25,546 citations
TL;DR: This paper summarizes the insights gained in automatic term weighting, and provides baseline single term indexing models with which other more elaborate content analysis procedures can be compared.
Abstract: The experimental evidence accumulated over the past 20 years indicates that textindexing systems based on the assignment of appropriately weighted single terms produce retrieval results that are superior to those obtainable with other more elaborate text representations. These results depend crucially on the choice of effective term weighting systems. This paper summarizes the insights gained in automatic term weighting, and provides baseline single term indexing models with which other more elaborate content analysis procedures can be compared.
9,460 citations
TL;DR: As a result of this grant, the researchers have now published on CDROM a corpus of over 4 million words of running text annotated with part-of- speech (POS) tags, which includes a fully hand-parsed version of the classic Brown corpus.
Abstract: : As a result of this grant, the researchers have now published oil CDROM a corpus of over 4 million words of running text annotated with part-of- speech (POS) tags, with over 3 million words of that material assigned skeletal grammatical structure This material now includes a fully hand-parsed version of the classic Brown corpus About one half of the papers at the ACL Workshop on Using Large Text Corpora this past summer were based on the materials generated by this grant
8,377 citations
Book•
01 Jan 19523,764 citations
TL;DR: In this paper, the 100th anniversary of Galton's first discussion of regression and correlation is celebrated, and 13 different formulas representing a different computational and conceptual definition of Pearson's r are presented.
Abstract: In 1885, Sir Francis Galton first defined the term “regression” and completed the theory of bivariate correlation. A decade later, Karl Pearson developed the index that we still use to measure correlation, Pearson's r. Our article is written in recognition of the 100th anniversary of Galton's first discussion of regression and correlation. We begin with a brief history. Then we present 13 different formulas, each of which represents a different computational and conceptual definition of r. Each formula suggests a different way of thinking about this index, from algebraic, geometric, and trigonometric settings. We show that Pearson's r (or simple functions of r) may variously be thought of as a special type of mean, a special type of variance, the ratio of two means, the ratio of two variances, the slope of a line, the cosine of an angle, and the tangent to an ellipse, and may be looked at from several other interesting perspectives.
3,251 citations