Brain Language Metrics on Earnings Calls - 4500+ US Stocks

The exploitation of textual unstructured content (news, company filings, earnings calls etc) in financial analysis is quickly expanding across both quantitative and discretionary strategies as demonstrated by the growing number of academic papers and products in this domain. The Brain Language Metrics on Earnings Calls Transcripts (BLMECT) dataset has the objective of monitoring several language metrics the quarterly earnings call transcripts for 4500+ US stocks. The dataset is made of two parts; one includes the language metrics for the most recent earnings call transcript for each stock, namely: 1) Financial sentiment 2) Percentage of words belonging to financial domain classified by language types: - “Constraining” language - “Litigious” language - “Uncertainty” language 3) Readability score 4) Lexical metrics such as lexical density and richness 5) Text statistics such as the report length and the average sentence length The second part includes the differences between the most recent earnings call transcript and the previous one: 1) Difference of the various language metrics (e.g. delta sentiment, delta readability score delta, delta percentage of a specific language type etc.) 2) Similarity metrics between documents, also with respect to a specific language type (for example similarity with respect to “litigious” language or “uncertainty” language) The metrics calculation is reported separately for the following sections of the transcript: a) Management Discussion b) Analysts Questions c) Management Answers to Analysts Questions The dataset is updated with a daily frequency since new earnings calls transcripts are published every day for some of the universe stocks. Clearly the data for each stock will change on a quarterly basis when new earnings calls are published. The historical dataset is available from year 2012. Factsheet https://braincompany.co/assets/files/BLM_ECT_summary.pdf Data dictionary https://braincompany.co/assets/files/BLM_ECT_data_dictionary.pdf

搜集汇总

背景与挑战

背景概述

该数据集监控4500多只美国股票的季度财报电话会议记录，提供最新记录的语言指标（包括金融情感、语言类型分类、可读性分数等）以及与前一次记录的差异分析。指标计算涵盖会议的管理层讨论、分析师提问和管理层回答等部分，数据从2012年开始每日更新。