Stop word
A stop word is a word, often frequent and functional, that text-processing systems may exclude or give reduced weight because it offers limited task-specific information.
Natural Language Processing in Action, Second Edition
A stop word is a frequent function word that usually contributes relatively little substantive information to a phrase's meaning.
- How it is used
- Guides token filtering and n-gram design in NLP pipelines.
- How deep it goes
- Defines stop words, demonstrates filtering tradeoffs, and stops short of prescribing a universal list.
- Examples
- Uses stop-word lists, Python filtering, four-gram hierarchy examples, and common-token counts.
- What you can do after
- Apply it via a tailored filter while checking whether removed words encode relationships or ambiguity.
Read how Natural Language Processing in Action, Second Edition explains stop word →
Starting Data Analytics with Generative AI and Python
A stop word is a high-frequency function word that text-processing systems commonly exclude from analysis because it carries limited task-specific content.
- How it is used
- Removes common words during review cleaning to focus frequency analysis or keyword search on more relevant terms.
- How deep it goes
- Defines stop words and demonstrates language-specific filtering, while questioning whether removal is useful for every keyword search.
- Examples
- Uses Portuguese customer reviews to demonstrate filtering stop words and correcting a tokenizer that defaults to English.
- What you can do after
- Apply it via NLTK to filter Portuguese reviews and check whether the tokenizer matches the review language.
Read how Starting Data Analytics with Generative AI and Python explains stop word →
Elasticsearch in Action, Second Edition
A frequently occurring word that is commonly excluded or specially handled during text analysis because it contributes little to retrieval discrimination.
- How it is used
- Improves text-search analysis by excluding common words that contribute little to retrieval discrimination.
- How deep it goes
- Defines stop words, shows custom analyzer configuration and token output, but does not detail filter internals.
- Examples
- Uses English, German, and Hindi analyzers plus a custom English analyzer that turns “A dog is for a life” into “dog” and “life.”
- What you can do after
- Operate and configure Elasticsearch analyzers with built-in or user-defined stop-word lists, then verify token output.
Read how Elasticsearch in Action, Second Edition explains stop word →
Just Use Postgres!
A stop word is a frequent function word, such as an article or preposition, that is excluded during text normalization because it contributes little search meaning.
- How it is used
- Supports Postgres full-text search by reducing documents and queries to meaningful lexemes.
- How deep it goes
- Explains removal during normalization and preserved positions, but defers detailed dictionary and configuration behavior.
- Examples
- Uses movie descriptions, to_tsvector output, and the phrase “The Lion King” to demonstrate omission and positional effects.
- What you can do after
- Apply stop-word-aware normalization with PostgreSQL’s to_tsvector and query-conversion functions.
Transfer Learning for Natural Language Processing
A word commonly filtered from text during processing because it is often considered less informative than other words.
- How it is used
- Uses stop-word removal to prepare email and movie-review text for classification.
- How deep it goes
- Defines frequent words as uninformative and demonstrates NLTK removal, but leaves the review-specific treatment largely unexplored.
- Examples
- Uses email words “the” and “are” and discusses preserving review negations such as “no” and “not.”
- What you can do after
- Apply stop-word removal with NLTK’s English list after tokenizing text.
Read how Transfer Learning for Natural Language Processing explains stop word →
Also covered in
What to know first
- bag-of-words modelA bag-of-words model represents text using word or token occurrences, counts, or weights while disregarding their order and syntactic relationships.
- similarity searchSimilarity search is a retrieval technique that finds or ranks items by their similarity to a query, often by comparing feature or vector representations under a similarity or distance measure.
- natural language processingNatural language processing is the field of computing concerned with computational methods for analyzing, interpreting, transforming, and generating human language in text or speech.
- data frameA data frame is a two-dimensional tabular data structure organized into labeled rows and columns, often with columns that can contain different types of values.
Related concepts
- normalizationused by · Normalization is the process of transforming or organizing data or representations according to rules to achieve a consistent form, scale, or structure.
- preprocessingused by · Preprocessing is the preparation or transformation of data or other inputs into a form suitable for subsequent processing, analysis, or execution.
- NLTKused by · NLTK, the Natural Language Toolkit, is an open-source Python library that provides tools and resources for natural-language processing and analysis of human-language data.
- tsqueryused by · tsquery is a PostgreSQL data type representing a normalized full-text search query composed of lexemes and search operators.
- bag-of-words modelused by · A bag-of-words model represents text using word or token occurrences, counts, or weights while disregarding their order and syntactic relationships.
Questions about stop word
What is stop word?
A stop word is a word, often frequent and functional, that text-processing systems may exclude or give reduced weight because it offers limited task-specific information.
Which Manning books explain stop word?
Natural Language Processing in Action, Second Edition, Starting Data Analytics with Generative AI and Python, Elasticsearch in Action, Second Edition, Just Use Postgres! and Transfer Learning for Natural Language Processing.
What should I know before learning stop word?
Manning books that teach stop word usually introduce bag-of-words model, similarity search, natural language processing and data frame first.
What is stop word a kind of?
Stop word is a kind of word. A word is a meaningful lexical unit of spoken or written language, typically represented by one or more characters.
What is stop word also called?
Stop word is also called stopword.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.




