Metric definitions
Approved NL Analytics metrics are integer sentence-count measures calculated at the earnings-call level.
Approved metrics
| Metric | Output variable | Definition | Calculation |
|---|---|---|---|
| Exposure | exposure | Number of sentences in an earnings call that contain at least one keyword from the user's query. | Count each sentence once if it contains at least one query keyword. |
| Risk | risk | Number of topic-matched sentences that also contain at least one risk or uncertainty synonym. | Count each sentence once if it contains at least one query keyword and at least one synonym for risk, risky, uncertain, or uncertainty. |
| Positive Sentiment | positive | Number of topic-matched sentences that also contain at least one positive sentiment word. | Count each sentence once if it contains at least one query keyword and at least one positive sentiment word. |
| Negative Sentiment | negative | Number of topic-matched sentences that also contain at least one negative sentiment word. | Count each sentence once if it contains at least one query keyword and at least one negative sentiment word. |
| Sentiment | sentiment | Net tone conditional on topic discussion. | positive - negative. |
Positive and negative sentiment words come from the Loughran-McDonald financial sentiment dictionary. The Risk synonym list is described as the deduplicated union of Oxford Thesaurus synonyms for risk, risky, uncertain, and uncertainty, excluding question, questions, and venture. NL Analytics excludes question and questions from the negative word list.
Calculation rules
The unit of analysis is a sentence inside an earnings-call transcript.
A sentence can contribute to Exposure if it contains at least one query keyword. A sentence can contribute to Risk, Positive Sentiment, or Negative Sentiment only after it first matches the topic query.
In the main Risk Tool counts, Positive Sentiment and Negative Sentiment are counted independently. A sentence that contains both positive and negative sentiment words contributes positive = 1, negative = 1, and net sentiment = 0.
Overall risk and sentiment
Some Risk Tool exports include overall risk and sentiment counts that are not conditioned on the user's query. These counts are useful when an analysis needs to compare topic-linked risk or sentiment with all risk or sentiment language in the same call.
At the call level:
- Overall Risk counts sentences with at least one risk or uncertainty synonym.
- Overall Positive Sentiment counts sentences with at least one positive sentiment word.
- Overall Negative Sentiment counts sentences with at least one negative sentiment word.
- Overall Sentiment is Overall Positive Sentiment minus Overall Negative Sentiment.
These overall counts are supporting outputs. They do not replace the topic-conditioned metrics in the main search output.
What the metrics do not mean
Metrics are raw counts. Do not interpret them as percentages, probabilities, classifier labels, causal estimates, forecasts, investment recommendations, or complete measures of real-world risk.
Exposure measures how much a call discusses the query topic. It does not prove the topic is important outside the selected corpus and query design.
Risk measures topic-linked risk discussion. It is not a compliance determination or a full risk assessment.
Sentiment is conditional on topic-matched sentences. It is not a standalone positive or negative classification of the whole call.
Filter caveat
The main fast-search counts and dataset-level sentiment filters do not use identical sentiment logic.
Main fast-search counts allow a mixed positive-and-negative sentence to count toward both positive and negative.
Dataset-level sentiment filters are stricter: positive means positive-only, negative means negative-only, and sentiment means either one-sided positive or one-sided negative. Mixed positive-and-negative sentences are excluded by those filters.