Stop Words

For data backed by an Analytic Index, Stop Words are the terms that Document Similarity operations, Word List generation, and Clustering operations automatically ignore by default. Ignoring words like articles, pronouns, and prepositions enables the software to focus similarity comparisons and Cluster representations on meaningful terms.

By default, Stop Words are ignored during the preparation of an Advanced Analytics Index for a Data Set. However, if you want Stop Words included as valid terms during indexing and parsing, a user with the appropriate permissions can modify the Include Stop Words setting in the Project Settings under Index Settings.

Note: Analytic Indexes also observe a minimum term length setting of 3 (to avoid common short words, one- and two-letter words), as well as a maximum term length setting of 32 characters. The Stop Words list happens to include many of the short words, but only words appearing on the actual Stop Words list are affected by the Stop Words setting.

Stop Words Notes:

• Enabling Stop Words for Clustering, Similarity Searches, or Word List generation must be done before a Data Set is Indexed. If the Stop Words setting changes after Indexing, the Data Set must be essentially reprocessed.

Stop Words by Language

For convenience, Stop Words are listed here in separate tables as English, Spanish, French, and HTML code stop words. However, Digital Reef uses a single combined stop words list.

English Stop Words

Spanish Stop Words