Papers › Constructing a Polarity Based Dictionary for Financial Language
Constructing a Polarity Based Dictionary for Financial Language
Lucy Chenhui Li, Amir Amel-Zadeh
Extracting and quantifying features from noisy financial language is an ex- tremely difficult task, especially without the availability of abundant computing resources. It is often difficult to assess whether language description on com- pany performance adhere to the realities of financial metrics. Organizations and researchers would benefit from using a general-purpose financial language dictio- nary to quantify financial performance. Currently, the only set of dictionaries widely available is the Loughran McDonald [LM11] dictionary, but this resource only quantifies sentiment. We instead seek to develop open sourced toolkit that would allow researchers to dive deeper into the content of financial accounting texts. Our paper aims to develop such a dictionary over vocabulary from 87,834 management disclosure and analysis sections over the years 1998 - 2021. Using relevant financial indicators of the associated years, we show that the dictionaries we construct to statistically accurately reflect financial performance.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections