ERIC Number: ED215680
Record Type: RIE
Publication Date: 1980-Oct-15
Reference Count: 0
A Method for Correcting Typographical Errors in Subject Headings in OCLC Records. Research Report.
O'Neill, Edward T.; Aluri, Rao
The error-correcting algorithm described was constructed to examine subject headings in online catalog records for common errors such as omission, addition, substitution, and transposition errors, and to make needed changes. Essentially, the algorithm searches the authority file for a record whose primary key exactly matches the test key. If an exact match is not found, the algorithm identifies records in the authority file, first with the same initial characters, or if that is unsuccessful, with similar endings. The heading is then examined to see if by making simple changes, it can be modified to match a valid record in the authority file. If no match can be found, even after modification, it is then assumed that the heading is one of questionable validity--being either a valid heading with no corresponding record in the author file or an invalid heading containing extensive errors. The algorithm separates the subject headings into groups of valid headings, corrected headings, and questionable headings that require manual examination. Provided are one table, five figures, and 21 references. (Author/RBF)
Publication Type: Reports - Research
Education Level: N/A
Authoring Institution: OCLC Online Computer Library Center, Inc., Dublin, OH.
Identifiers: Authority Files; Error Detection; Library of Congress Subject Headings; OCLC