Glossary

Text analytics

The techniques used to extract structured information and insight from unstructured text, from keyword counts to deep NLP.

Text analytics is the umbrella term for the set of techniques used to turn unstructured text into structured, analyzable data, ranging from simple keyword and frequency counts to deep natural language processing.

It encompasses more specific techniques such as sentiment analysis for opinion, topic modeling for theme discovery, and Named Entity Recognition for extracting specific facts, and increasingly draws on general-purpose large language models that can perform several of these tasks at once through a single prompt rather than separate purpose-built models. This differs from full natural language understanding in that many text analytics tasks aim at extracting one structured signal rather than genuinely comprehending meaning.

Organizations apply text analytics to customer support tickets, product reviews, and survey responses, as well as content collected through social listening, turning volumes of free text no analyst could read individually into dashboards and trends. The main pitfalls are applying a model trained on one domain or language to another where it performs poorly, and treating extracted signals as ground truth without spot-checking against the original text.

Last reviewed September 22, 2026

In the index now

Related terms

Sentiment analysis Using NLP to classify text as positive, negative, or neutral, so large volumes of comments or reviews can be scored automatically. Topic modeling An unsupervised machine learning technique that discovers the latent themes running through a collection of documents. Named Entity Recognition (NER) An NLP technique that locates and classifies names of people, organizations, places, and other entities within text. Semantic search Search that matches results to a query's meaning rather than its exact keywords, using vector similarity between embeddings. Large language model (LLM) A neural network trained on vast amounts of text to predict and generate language, the technology behind most modern AI assistants.

Related tools

CallMiner Contact-centre conversation analytics that transcribes and scores 100% of agent calls for compliance, quality and sentiment. Gensim Open-source Python library for unsupervised topic modeling and document-similarity analysis using vector-space methods. Greenplum Open-source, massively parallel PostgreSQL-based data warehouse for large-scale analytical SQL. Hugging Face Transformers Open-source Python library providing pretrained transformer models for text, vision and audio tasks. Lexalytics Enterprise text-analytics and NLP platform offering sentiment, entity and intent extraction for business applications. NLTK Open-source Python library and teaching toolkit for classic natural-language-processing tasks and research.

Related guides

How to analyze text data From word counts and topic models to LLM classification — matching the method to the question instead of reaching for the newest tool by default. How to choose a digital humanities tool Digital humanities tools split by what they analyze — text, networks, images or structured historical data — pick by your source material, not the category. How to choose a text analytics or NLP tool Pick an NLP library or platform by whether your team writes code, what task you're actually doing, and whether you need a pretrained model or a custom one.