Stop word

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Stop words are any word in a stop list (or stoplist or negative dictionary) which are filtered out (i.e. stopped) before or after processing of natural language data (text).[1] There is no single universal list of stop words used by all natural language processing tools, nor any agreed upon rules for identifying stop words, and indeed not all tools even use such a list. Therefore, any group of words can be chosen as the stop words for a given purpose. The "general trend in [information retrieval] systems over time has been from standard use of quite large stop lists (200–300 terms) to very small stop lists (7–12 terms) to no stop list whatsoever"[2]

History of stop words[edit]

A predecessor concept was used in creating some concordances. For example, the first Hebrew concordance, Me’ir nativ, contained a one-page list of unindexed words, with nonsubstantive prepositions and conjunctions which are similar to modern stop words.[3]

Hans Peter Luhn, one of the pioneers in information retrieval, is credited with coining the phrase and using the concept when introducing his Keyword-in-Context automatic indexing process.[4] The phrase "stop word", which is not in Luhn's 1959 presentation, and the associated terms "stop list" and "stoplist" appear in the literature shortly afterward.[5]

Although it is commonly assumed that stoplists include only the most frequent words in a language, it was C.J. Van Rijsbergen who proposed the first standardized list which was not based on word frequency information. The "Van list" included 250 English words. Martin Porter's word stemming program developed in the 1980s built on the Van list, and the Porter list is now commonly used as a default stoplist in a variety of software applications.

In 1990, Christopher Fox proposed the first general stop list based on empirical word frequency information derived from the Brown Corpus:

This paper reports an exercise in generating a stop list for general text based on the Brown corpus of 1,014,000 words drawn from a broad range of literature in English. We start with a list of tokens occurring more than 300 times in the Brown corpus. From this list of 278 words, 32 are culled on the grounds that they are too important as potential index terms. Twenty-six words are then added to the list in the belief that they may occur very frequently in certain kinds of literature. Finally, 149 words are added to the list because the finite state machine based filter in which this list is intended to be used is able to filter them at almost no cost. The final product is a list of 421 stop words that should be maximally efficient and effective in filtering the most frequently occurring and semantically neutral words in general literature in English.[6]

In SEO terminology, stop words are the most common words that many search engines avoid, for the purposes of saving space and time in processing of large data during crawling or indexing. This helps search engines to save space in their databases.[7]

For some search engines, these are some of the most common, short function words, such as the, is, at, which, and on. In this case, stop words can cause problems when searching for phrases that include them, particularly in names such as "The Who", "The The", or "Take That". Other search engines remove some of the most common words—including lexical words, such as "want"—from a query in order to improve performance.[8]

See also[edit]

References[edit]

  1. ^ Rajaraman, A.; Ullman, J. D. (2011). "Data Mining" (PDF). Mining of Massive Datasets. pp. 1–17. doi:10.1017/CBO9781139058452.002. ISBN 9781139058452.
  2. ^ Christopher D. Manning, Prabhakar Raghavan, Hinrich Schütze (2008). Introduction to Information Retrieval. Cambridge University Press. p. 27.CS1 maint: multiple names: authors list (link)
  3. ^ Weinberg, Bella Hass (2004). "Predecessors of scientific indexing structures in the domain of religion" (PDF). Second Conference on the History and Heritage of Scientific and Technical Information Systems: 126–134. Retrieved 17 February 2016.
  4. ^ Luhn, H. P. (1959). "Keyword-in-Context Index for Technical Literature (KWIC Index)". American Documentation. Yorktown Heights, NY: International Business Machines Corp. 11 (4): 288–295. doi:10.1002/asi.5090110403.
  5. ^ Flood, Barbara J. (1999). "Historical note: The Start of a Stop List at Biological Abstracts". Journal of the American Society for Information Science. 50 (12): 1066. doi:10.1002/(SICI)1097-4571(1999)50:12<1066::AID-ASI5>3.0.CO;2-A.
  6. ^ Fox, Christopher (1989-09-01). "A stop list for general text". ACM SIGIR Forum. 24 (1–2): 19–21. doi:10.1145/378881.378888. ISSN 0163-5840.
  7. ^ "Stop Words and Impact on SEO - Search Engine Nation". Search Engine Nation. 2018-04-24. Retrieved 2018-05-24.
  8. ^ Stackoverflow: "One of our major performance optimizations for the "related questions" query is removing the top 10,000 most common English dictionary words (as determined by Google search) before submitting the query to the SQL Server 2008 full text engine. It’s shocking how little is left of most posts once you remove the top 10k English dictionary words. This helps limit and narrow the returned results, which makes the query dramatically faster".

External links[edit]