{"data":{"id":"10.4231/r7mk6b49","type":"dois","attributes":{"doi":"10.4231/r7mk6b49","prefix":"10.4231","suffix":"r7mk6b49","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Seliger, Corey","givenName":"Corey","familyName":"Seliger","affiliation":["Purdue University"],"nameIdentifiers":[{"schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-6100-3959","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"Text Mining and Plotting Tools for KSA / DS / HEI Research Study"}],"publisher":"Purdue University Research Repository","container":{},"publicationYear":2018,"subjects":[{"subject":"Software source code"},{"subject":"Java"},{"subject":"Python"},{"subject":"RStudio"},{"subject":"CoreNLP"},{"subject":"NLP"},{"subject":"Unstructured Text"},{"subject":"ggplot2"},{"subject":"FOS: Electrical engineering, Electronic engineering, Information engineering","schemeUri":"https://web-archive.oecd.org/2012-06-15/138575-38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)","classificationCode":"2.2"}],"contributors":[{"name":"Seliger, Corey","nameType":"Personal","givenName":"Corey","familyName":"Seliger","affiliation":["Purdue University"],"contributorType":"ContactPerson","nameIdentifiers":[{"schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-6100-3959","nameIdentifierScheme":"ORCID"}]}],"dates":[{"date":"2018-07-25","dateType":"Available"},{"date":"2018-07-25","dateType":"Submitted"},{"date":"2018-07-25","dateType":"Accepted"},{"date":"2018","dateType":"Issued"}],"language":"en","types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Datasets","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[{"relationType":"References","relatedIdentifier":"10.3115/v1/p14-5010","resourceTypeGeneral":"ConferencePaper","relatedIdentifierType":"DOI"},{"relationType":"IsReferencedBy","relatedIdentifier":"https://www.proquest.com/dissertations-theses/exploring-knowledge-skills-abilities-data-science/docview/2111256730/se-2","resourceTypeGeneral":"Dissertation","relatedIdentifierType":"URL"}],"relatedItems":[],"sizes":["22 files","328 KB"],"formats":["text/xml","text/x-java","text/x-c","text/x-script.python","text/plain","application/pdf"],"version":"1.0","rightsList":[{"rights":"GNU General Public License v3.0 only","rightsUri":"https://www.gnu.org/licenses/gpl-3.0-standalone.html","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"gpl-3.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"\u0026lt;p\u0026gt;This publication contains three major utilities: 1) An example web scraper used to pull position descriptions from internet websites. 2) TextCleanupTools, a set of Java programs written against the Stanford CoreNLP library to analyze and parse unstructured text from position descriptions and course curricula data. 3) A set of R scripts used to plot various data points extracted from the analyzed text.\u0026amp;nbsp;\u0026lt;/p\u0026gt;","descriptionType":"Abstract"},{"description":"This publication comprises the source code for various text mining utilities written against the Stanford CoreNLP project and other scripts to plot the formatted output from those programs.","descriptionType":"Other"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://purr.purdue.edu/publications/3041/1","contentUrl":null,"metadataVersion":6,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":1,"citationCount":0,"citationsOverTime":[{"year":"2025","total":1}],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2018-07-24T21:08:35.000Z","registered":"2018-07-24T21:09:48.000Z","published":"2018","updated":"2025-12-18T21:02:31.000Z"},"relationships":{"client":{"data":{"id":"purdue.purduelib","type":"clients"}},"provider":{"data":{"id":"purdue","type":"providers"}},"media":{"data":{"id":"10.4231/r7mk6b49","type":"media"}},"references":{"data":[{"id":"10.3115/v1/p14-5010","type":"dois"}]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}