zenodoopen

Aggregated Earnings Call Dataset

Aggregated Earnings Call Dataset for the paper "FLAG: Financial Long Document Regression via AMR-based GNN" It contained earnings calls data, along with associated price data, that we collected from companies in the S&P 1500 Composite Index from 2010 to 2019. CSV files without "tech" in their filenames contain the full amount of earnings calls we collected, and CSV files with "tech" in their filenames contain the portion of the dataset from the technology sector, which we use in the experiments detailed in the paper.

ShareScore

40/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship: 8
Harmonization: 4
Access: 20
Reuse readiness: 8
Engagement: 0

Topics

text regression language models long text documents natural language processing text mining machine learning information extraction financial documents earnings calls graph neural networks deep learning