Automatic keyword extraction from individual documents is a method to identify important terms within a text. Keywords are essential for information retrieval (IR) systems as they are easy to define, revise, and share. Unlike mathematical signatures, keywords are independent of any corpus and can be applied across multiple corpora and IR systems. Keywords can enhance IR systems by improving search functionality and enriching search results. Various methods have been developed to extract keywords automatically, including corpus-oriented and document-oriented approaches. Corpus-oriented methods rely on statistical analysis of word frequencies across a corpus, while document-oriented methods focus on individual documents and are more suitable for dynamic collections. RAKE is an unsupervised, domain-independent, and language-independent method for extracting keywords from individual documents. It uses stop words and phrase delimiters to partition the text into candidate keywords, which are sequences of content words. Co-occurrences of words within these candidate keywords are used to measure word associations and score candidate keywords. RAKE is more computationally efficient than TextRank while achieving higher precision and comparable recall scores. It also includes a novel method for generating stoplists, which can be configured for specific domains and corpora. RAKE was tested on a benchmark dataset of technical abstracts and showed superior performance in terms of precision, efficiency, and simplicity. It was also applied to a corpus of news articles, where it extracted keywords that represented the essential content of the documents. The extracted keywords were evaluated based on their exclusivity, essentiality, and generality. RAKE's simplicity and efficiency make it suitable for a wide range of applications where keywords can be leveraged. It provides advantages in terms of computational efficiency and frees up resources for other analytic methods. RAKE is particularly effective for dynamic collections such as collections of published technical abstracts and streams of news articles.Automatic keyword extraction from individual documents is a method to identify important terms within a text. Keywords are essential for information retrieval (IR) systems as they are easy to define, revise, and share. Unlike mathematical signatures, keywords are independent of any corpus and can be applied across multiple corpora and IR systems. Keywords can enhance IR systems by improving search functionality and enriching search results. Various methods have been developed to extract keywords automatically, including corpus-oriented and document-oriented approaches. Corpus-oriented methods rely on statistical analysis of word frequencies across a corpus, while document-oriented methods focus on individual documents and are more suitable for dynamic collections. RAKE is an unsupervised, domain-independent, and language-independent method for extracting keywords from individual documents. It uses stop words and phrase delimiters to partition the text into candidate keywords, which are sequences of content words. Co-occurrences of words within these candidate keywords are used to measure word associations and score candidate keywords. RAKE is more computationally efficient than TextRank while achieving higher precision and comparable recall scores. It also includes a novel method for generating stoplists, which can be configured for specific domains and corpora. RAKE was tested on a benchmark dataset of technical abstracts and showed superior performance in terms of precision, efficiency, and simplicity. It was also applied to a corpus of news articles, where it extracted keywords that represented the essential content of the documents. The extracted keywords were evaluated based on their exclusivity, essentiality, and generality. RAKE's simplicity and efficiency make it suitable for a wide range of applications where keywords can be leveraged. It provides advantages in terms of computational efficiency and frees up resources for other analytic methods. RAKE is particularly effective for dynamic collections such as collections of published technical abstracts and streams of news articles.