Definition
Text mining converts unstructured text — complaints, service notes, open survey answers, reports — into structured data that statistics can work with. Documents are broken into words and word stems, frequencies and weighted matrices (TF-IDF) are computed, and clustering, classification or topic discovery run on top of them.
Data mining & machine learning
Typical tasks: automatic sorting of complaints by cause, finding recurring problems in service records, sentiment analysis of customer reviews or linking text with numeric data (how much do defects described by certain words cost).
Preprocessing is key: stop words, lemmatization or stemming, synonyms and a domain dictionary. The resulting document × word matrix is usually reduced by singular value decomposition (SVD) before modelling — otherwise thousands of columns overwhelm even robust methods.
In Statistica
The Text Mining module in the Data Mining menu loads documents from files, databases or the web, applies stemming for many languages, builds a frequency matrix with TF-IDF weighting, reduces it via SVD and hands the results to clustering, trees or neural networks in the Workspace environment; word frequencies and concepts are shown in interactive graphs.
Related terms
- Cluster analysisCluster analysis divides observations into groups (clusters) so that units within a cluster are as similar as possible…
- Principal component analysis (PCA)Principal component analysis (PCA) condenses many correlated variables into a few new uncorrelated components that…
- Decision treesA decision tree splits data by a sequence of simple rules ("age > 45 and income < 30 thousand") into ever more…
- Missing dataMissing data are gaps in the dataset — an unmeasured sample, an unanswered question, a sensor outage.
Knowledgebase guides
FAQ
- Does text mining handle Czech and other languages?
- Yes — the basis is stemming and a custom stop-word list; for technical texts it pays to add synonyms and abbreviations from your field.
- How many documents are needed?
- Hundreds suffice for descriptive analysis, thousands of labelled documents for reliable classification.
Try it on your own data
Statistica free for 30 days
Full version, no credit card. Or get a pricing estimate in a minute.
Data mining & machine learning
Updated: September 2026.