# DisclosuR: Advancing firm communication analysis through an innovative R package for enhanced textual insights

## TL;DR

The disclosuR R package helps researchers analyze firm communications by converting unstructured PDFs into structured data for detailed text analysis.

## Contribution

disclosuR introduces unique features like speaker-level language analysis and temporal pattern detection in firm communication data.

## Key findings

- disclosuR converts LexisNexis PDFs into structured R data frames for analysis.
- The package enables reproducible and granular quantitative analysis of firm communication.
- It supports advanced text analysis, including speaker-level insights and temporal communication patterns.

## Abstract

Firm and executive written communication allows researchers to explore firm strategy and executive personality. Two data sources have received increased interest in this matter: firm press releases and earnings call transcripts. However, while researchers can obtain these data sources through services like LexisNexis, they often come in unstructured formats that do not directly allow fine-grained quantitative analysis through statistical software. To address this challenge, we developed disclosuR, an innovative R package that transforms unstructured PDF press releases and earnings call transcripts into structured data frames, facilitating advanced text analysis. disclosuR stands out by providing unique features such as speaker-level language analysis and identifying temporal communication patterns within press releases. These functionalities empower researchers to conduct granular and reproducible quantitative analyses, significantly advancing the management literature. By enabling the seamless integration of text data into R, our package not only enhances the reproducibility of social science research but also opens new avenues for examining executive communication dynamics and strategic firm disclosures.•Convert LexisNexis PDFs to structured R data frames•Standardize text analysis of firm communication

Convert LexisNexis PDFs to structured R data frames

Standardize text analysis of firm communication

Image, graphical abstract