{"id":{"repo_id":"byu","oai_identifier":"oai:scholarsarchive.byu.edu:etd-2183"},"canonical_url":"https://search.dev.ndltd.org/etd/byu/oai:scholarsarchive.byu.edu:etd-2183","repository":{"repo_id":"byu","name":"Brigham Young University","base_url":"https://scholarsarchive.byu.edu/do/oai/"},"display":{"title":"Text Identification by Example","abstract":"The World-Wide Web contains a lot of information and reading through the web pages to collect this information is tedious, time consuming and error prone. Users need an automated solution for extracting or highlighting the data that they are interested in. Building a regular expression to match the text they are interested in will automate the process, but regular expressions are hard to create and certainly are not feasible for non-programmers to construct. Text Identification by Example (TIBE) makes it easier for end-users to harvest information from the web and other text documents. With TIBE, training text classifiers from user-selected positive and negative examples replaces the hand-writing of regular expressions. The text classifiers can then be used to extract or highlight text on web pages.","abstract_html":"The World-Wide Web contains a lot of information and reading through the web pages to collect this information is tedious, time consuming and error prone. Users need an automated solution for extracting or highlighting the data that they are interested in. Building a regular expression to match the text they are interested in will automate the process, but regular expressions are hard to create and certainly are not feasible for non-programmers to construct. Text Identification by Example (TIBE) makes it easier for end-users to harvest information from the web and other text documents. With TIBE, training text classifiers from user-selected positive and negative examples replaces the hand-writing of regular expressions. The text classifiers can then be used to extract or highlight text on web pages.","abstract_has_math":false,"creators":["Preece, Daniel Joseph"],"institution":"Brigham Young University - Provo","degree_name":"MS","degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-07-24T01:28:54Z","subjects":["pattern matching","text identification","examples","concept modeling","classifier","training","Computer Sciences"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://scholarsarchive.byu.edu/etd/1184","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Preece, Daniel Joseph"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2007-08-02T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Brigham Young University - Provo"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["pattern matching","text identification","examples","concept modeling","classifier","training","Computer Sciences"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://scholarsarchive.byu.edu/etd/1184","https://scholarsarchive.byu.edu/context/etd/article/2183/viewcontent/ETD_CISOPTR_1188.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Physical and Mathematical Sciences; Computer Science"]},{"key":"dc:description.abstract","label":"Abstract","values":["The World-Wide Web contains a lot of information and reading through the web pages to collect this information is tedious, time consuming and error prone. Users need an automated solution for extracting or highlighting the data that they are interested in. Building a regular expression to match the text they are interested in will automate the process, but regular expressions are hard to create and certainly are not feasible for non-programmers to construct. Text Identification by Example (TIBE) makes it easier for end-users to harvest information from the web and other text documents. With TIBE, training text classifiers from user-selected positive and negative examples replaces the hand-writing of regular expressions. The text classifiers can then be used to extract or highlight text on web pages."]},{"key":"dc:format","label":"Dc Format","values":["application:pdf"]},{"key":"dc:source","label":"Dc Source","values":["Brigham Young University - Provo"]},{"key":"dc:title","label":"Title","values":["Text Identification by Example"]}]}],"canonical_facts":{"dc:creator":["Preece, Daniel Joseph"],"dc:date":["2007-08-02T07:00:00Z"],"dc:description":["Physical and Mathematical Sciences; Computer Science"],"dc:description.abstract":["The World-Wide Web contains a lot of information and reading through the web pages to collect this information is tedious, time consuming and error prone. Users need an automated solution for extracting or highlighting the data that they are interested in. Building a regular expression to match the text they are interested in will automate the process, but regular expressions are hard to create and certainly are not feasible for non-programmers to construct. Text Identification by Example (TIBE) makes it easier for end-users to harvest information from the web and other text documents. With TIBE, training text classifiers from user-selected positive and negative examples replaces the hand-writing of regular expressions. The text classifiers can then be used to extract or highlight text on web pages."],"dc:format":["application:pdf"],"dc:identifier":["https://scholarsarchive.byu.edu/etd/1184","https://scholarsarchive.byu.edu/context/etd/article/2183/viewcontent/ETD_CISOPTR_1188.pdf"],"dc:language":["English"],"dc:publisher":["Brigham Young University - Provo"],"dc:source":["Brigham Young University - Provo"],"dc:subject":["pattern matching","text identification","examples","concept modeling","classifier","training","Computer Sciences"],"dc:title":["Text Identification by Example"],"dc:type":["Thesis"],"thesis:degree_name":["MS"]},"updated_at":"2026-07-24T01:28:54Z"}