Formula used
How to use the calculator
- Paste text or upload supported document files.
- Add documents when comparison or TF-IDF is required.
- Select cleaning, tokenisation, and stop-word options.
- Choose frequency, n-gram, and vocabulary settings.
- Press the analysis button to generate results.
- Review tables, matrices, similarities, and visual charts.
- Copy or export results in your preferred format.
Example data
| Example text | Word | Count | Relative frequency | Percentage |
|---|---|---|---|---|
| Machine learning learns patterns. Machine learning uses data. | machine | 2 | 0.25 | 25% |
| Machine learning learns patterns. Machine learning uses data. | learning | 2 | 0.25 | 25% |
Frequently asked questions
What is word frequency?
Word frequency counts how often each token appears. It supports text exploration and feature creation.
How does TF-IDF differ from frequency?
Frequency measures repetition within text. TF-IDF reduces scores for widely shared terms.
Why remove stop words?
Stop words can dominate results without adding meaning. Removing them highlights more informative vocabulary.
What are n-grams?
N-grams are consecutive sequences of tokens. They reveal common phrases and contextual patterns.
What is lexical diversity?
Lexical diversity compares unique words with total words. Higher values indicate broader vocabulary use.
Can several documents be compared?
Yes. Add documents to calculate document frequency, TF-IDF, matrices, and cosine similarity.
What is a document-term matrix?
It stores document rows and vocabulary columns. Values represent counts or binary word presence.
Does stemming equal lemmatisation?
No. Stemming trims endings mechanically. Lemmatisation attempts to return a meaningful base form.
Which files are supported?
The calculator accepts TXT, CSV, and JSON files. Each file is processed as readable text.