Show simple item record

dc.contributor.advisorElsa Olivetti.en_US
dc.contributor.authorMulcahy, Ciara(Ciara Renee)en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Materials Science and Engineering.en_US
dc.date.accessioned2021-06-17T17:21:25Z
dc.date.available2021-06-17T17:21:25Z
dc.date.copyright2020en_US
dc.date.issued2020en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/131011
dc.descriptionThesis: S.B., Massachusetts Institute of Technology, Department of Materials Science and Engineering, May, 2020en_US
dc.descriptionCataloged from the official PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 33-35).en_US
dc.description.abstractPlastics are commercially produced by selecting a polymer resin and incorporating chemical additives to affect specific mechanical, chemical or aesthetic properties of the plastic products. The number of possible combinations of polymers and additives yields an enormous engineering space to meet the design requirements of the many applications of plastic materials. However, the broad scope of plastics science hinders both the invention of new plastics formulations and efforts to investigate potentially harmful polymer resins and plastic additives. In this thesis, a method of representing and analyzing the claims section of patents is presented and applied to a set of patents that refer to flame retardants. The claims section of a patent is presented as a graph, with individual claims as points and references between claims as lines connecting those points.en_US
dc.description.abstractThe chemical terms mentioned in the text of each of the claims were split into individual words or short sequences of words, called "tokens", by an existing materials tokenizer that had been trained on scientific journal articles. The term frequency - inverse document frequency (tf-idf) statistic for each token within each claim was computed, using the entire claims section of the individual patent to calculate the document frequency. Each claim was attributed the tokens that had tf-idf scores greater than the highest-scoring term shared with a claim to which that claim referred. By researcher inspection, this method served to extract relevant chemical terms, while omitting words that did not contribute to the chemical relevance of the claim or patent as a whole. A visualization of these labelled graphs of the claims was generated.en_US
dc.description.abstractThis reduced, graphical representation of materials patents could be implemented to aid in researcher review or computational tasks to survey for chemical components or resin-additive compatibilities. Such a representation of patent data could make the prioritization and review of commercial chemicals a more tractable task.en_US
dc.description.statementofresponsibilityby Ciara Mulcahy.en_US
dc.format.extent35 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectMaterials Science and Engineering.en_US
dc.titleAnalysis of patent data for flame-retardant plastics additivesen_US
dc.typeThesisen_US
dc.description.degreeS.B.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Materials Science and Engineeringen_US
dc.identifier.oclc1256550509en_US
dc.description.collectionS.B. Massachusetts Institute of Technology, Department of Materials Science and Engineeringen_US
dspace.imported2021-06-17T17:21:25Zen_US
mit.thesis.degreeBacheloren_US
mit.thesis.departmentMatScien_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record