NLP for tabular text data

Compute linguistic measures
on your text data.

Upload a spreadsheet. Pick the text column. Choose NLP measures. Get an enriched file back, with every score documented and reproducible.

1
Step one
Upload your data
Pick the language of your text, then drop your file.
🇺🇸
Drag & drop or browse
.csv .tsv .xlsx .parquet · up to 50 MB
No file handy?
2
Step two
Select the text column
Pick which column holds the text to be analyzed.
3
Step three

Choose measure categories

Each category adds a defined set of columns to your file. View all columns →
Surface statsfast
Word, character, sentence counts. Length, TTR, hapax, punctuation rate.
Readabilityfast
Flesch, Flesch-Kincaid, Gunning Fog, SMOG, Coleman-Liau, ARI, Dale-Chall.
Sentiment & emotionstandard
VADER, TextBlob polarity and subjectivity, NRC eight-emotion lexicon.
Linguistic structurestandard
POS proportions, pronouns by person, tense ratios, modals.
Syntactic complexitystandard
Dependency depth, clauses per sentence, T-unit length, subordination.
Lexical normsstandard
Concreteness, age-of-acquisition, valence, arousal, dominance, Zipf.
Style & AI detectionintensive
Perplexity, burstiness, hedges, certainty, intensifiers.
Rhetoric & persuasionfast
Hedging, boosting, politeness, question/imperative ratios, we-vs-I.
Named entitiesstandard
Counts of people, organizations, places, dates, money mentions.
0 categories · 0 new columns
Roadmap

Request a feature

Have an idea for a new linguistic measure, file format, language, or workflow improvement? We read every request.