Factor families

NLP tone (Loughran-McDonald)

In plain English

Reading the company's 10-K filing for negative-sounding words — companies whose MD&A is unusually negative tend to underperform.

How it works

Loughran-McDonald 2011 built the standard financial-sentiment dictionary (after showing that general English sentiment dictionaries fail catastrophically on financial text — "liability" is not a negative word in finance). Li 2008 showed that 10-K MD&A negativity has predictive power. We score the tone of the most recent 10-K MD&A section using LM-2018 dictionary; high negativity = bearish.

Where you see this in Framler
NLP factor card. Coloured red on the score waterfall when negative.
Primary citation
Loughran-McDonald 2011 + Li 2008

Related — Factor families

Quality factor (Novy-Marx)Value factor (Fama-French)Momentum factorPEAD (Post-earnings drift)Accruals signal (Sloan)Short interest (Asquith)

← All glossary terms · Full methodology →

NLP tone (Loughran-McDonald) — Framler glossary | Framler