0

As a non-native speaker of English, I struggle with the orthography of the word stop word. The term is used in the context of text mining, natural language processing and corpus linguistics. It refers to words which are usually ignored in subsequent text analyses due to their high frequency and/or their low informativity (e.g. most function words, auxiliary verbs etc.).

The headword in Wikipedia uses the two-word spelling stop word, but the one-word spelling stopword also seems to be rather frequent, for example in the NLTK documentation or the MySQL references.

Which of the two spelling variants should I use? If you have a personal preference for either, I'd be happy to hear that. Please also add whether you're actually familiar with the term (e.g. because you work in the field of text analysis). This is particularly interesting because I'm going to use it in a software that is aimed at a technical audience.

  • Dictionary.com tells you what is/are considered acceptable. A quick glance online suggests to me that the open compound ('stop word') is more commonly used at the moment. – Edwin Ashworth Oct 12 '16 at 8:40
0

Both seems to be used nearly equally seeing google ngram. Personally, I have a preference for stop word.

  • 1
    Funny thing about Google Ngram is that stopword was clearly behind stop word before the year 2000, only to catch up later again. Interestingly, this seems to coincide with the time when the term gained much popularity due to technological advances in text processing. – Schmuddi Oct 12 '16 at 8:54
  • @Schmuddi I edited the link to include more years and have a better usage evolution pov. – Yohann V. Oct 12 '16 at 9:01
  • Interesting... So computer languages not allowing spaces in identifiers may be the culprit in the upsurge in stopword? – GEdgar Oct 12 '16 at 14:35
  • @GEdgar What do you think Watson? – Yohann V. Oct 12 '16 at 14:44

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.