Topic modeling

Sentiment analysis

Lemmatization

Tokenization

It applies fixed rules to all texts

It only stores linguistic information

It replaces the need for data

It enables systems to learn patterns and generalize from experience

It ignores meaning entirely

It replaces interpretation with visualization

It emphasizes large-scale patterns over close textual detail

It focuses only on non-literary texts

It is always incomplete

It lacks predefined organization, making standard processing difficult

It cannot be stored digitally

It contains only images

Text mining extracts patterns; text analytics interprets and presents them

Text mining is manual, while text analytics is automated

They are identical processes

Text analytics precedes text mining

Pragmatic context

Manual interpretation

Statistical regularities in language use

Semantic meaning

Search uses no algorithms

Search has a clear goal; discovery explores unknown patterns

Search is random; discovery is planned

Discovery requires no data

Using algorithms to detect recurring narrative patterns

Statistical clustering of literary themes

Analyzing thousands of novels for genre trends

Close analysis of metaphors in a single poem

Writing texts automatically

Discovering hidden patterns and insights in large text collections

Editing texts

Storing documents

Lemmatization

Tokenization

Parsing