This study develops, implements, and evaluates a multi-label text classification algorithm that extracts textual information from the annual reports of all publicly listed USA companies. Specifically, the proposed system can automatically identify 25 types of frequently mentioned risk factors in...

This study develops, implements, and evaluates a multi-label text classification algorithm called the multi-label categorical K - nearest neighbor (ML-CKNN). The proposed algorithm is designed to automatically identify 25 types of risk factors with specific meanings reported in Section 1A of SEC...

As an important indicator of earnings quality, earning persistence is perceived as the reflection of operation management and the quality of internal control. It facilitates the optimization of resource allocation and provides investors valuable insights. Strategy is described as the long-term...

Prior research generally interprets complex language in firms' disclosures as indicative of managerial obfuscation. However, complex language can also reflect the provision of complex information, e.g., informative technical disclosure. As a consequence, linguistic complexity commingles two...

Prior research generally interprets complex language in firms' disclosures as indicative of managerial obfuscation. However, complex language can also reflect the provision of complex information; for example, informative technical disclosure. As a consequence, linguistic complexity commingles...

We explore how the readability of annual reports varies with earnings management. Using the Fog Index to measure readability (Li 2008), and focusing on the management discussion and analysis section of the annual report (MD&A), we predict and find that firms most likely to have managed earnings...

This paper examines the relationship between annual report readability and firm performance and earnings persistence. This is motivated by the Securities and Exchange Commission's plain English disclosure regulations that attempt to make corporate disclosures easier to read for ordinary...

This paper examines the relation between annual report boilerplate and firm performance and earnings persistence. Utilizing a neural network algorithm inspired by word2vec, we compute the annual report boilerplate, defined as the average probability of the occurring of each sentence in a given...

We model limited attention as incomplete usage of publicly available information. Informed players decide whether or not to disclose to observers who sometimes neglect either disclosed signals or the implications of non-disclosure. In equilibrium observers are unrealistically optimistic,...

This paper explores the dynamics of transparency. It asks why some government-created systems of disclosure improve over time while others stagnate or degenerate into costly paperwork exercises. Transparency policies inevitably begin as unlikely compromises. Though transparency is universally...