NL Analytics documentation

Convert English earnings-call transcripts into auditable call-level measures for topic exposure, risk, and sentiment.

Key workflows

From research idea to panel: Follow the main workflow from a topic idea to an exported call-level panel.
Worked example: supply chain disruption: See every step applied to one concrete construct.
Corpus availability: Learn what the corpus contains and how to verify sample availability.
Terminology: Distinguish queries, searches, datasets, measures, and curated datasets.
Query syntax: Write keywords, phrases, Boolean logic, exclusions, and wildcard searches.
Measure definitions: Understand Exposure, Risk, Positive Sentiment, Negative Sentiment, and Sentiment.
Export a research panel: The output files, their columns, and identifiers for downstream joins.
Curated Measures: Maintained curated datasets for established constructs.
Known limitations: What the product and the measures do not do.

What NL Analytics does

NL Analytics turns matched earnings-call sentences into transparent call-level measures. The corpus is English earnings-call transcripts; you cannot upload your own text.

The core workflow is:

Start with a research question or topic.
Translate that idea into keywords, phrases, synonyms, and exclusions with the Keyword Tool.
Run a search with the Risk Tool to create a dataset.
Inspect the dataset's matched sentences in the Snippet Tool.
Refine the query until the matches support the intended construct.
Export the dataset's call-level CSV output for downstream work.

What the measures are

The core measures are raw integer sentence counts calculated at the earnings-call level:

Exposure counts topic-matched sentences.
Risk counts topic-matched sentences that also contain risk or uncertainty language.
Positive Sentiment and Negative Sentiment count topic-matched sentences that also contain financial sentiment words.
Sentiment is positive - negative.

See Measure definitions for the exact definitions and interpretation caveats. The counts are built from explicit queries and curated word lists, so every value can be traced back to inspectable matched sentences.

Before using results

Results depend on query design and corpus availability. Before treating an output as a measure, inspect matched sentences, check sample availability and variation in the target sample, and record the dataset per the reproducibility checklist.

Getting access. Create an account on the application's /signup page, or email [email protected] to have enterprise access provisioned for your team. There is no public end-user API; the product is used through the UI and CSV downloads.

Where to go next

Start with From research idea to panel if you are designing a new measure, or read the worked example first to see the full path once. Use Query syntax when you need exact matching rules, My Datasets when you need a prior dataset, and Get help when something does not behave as documented.