10.4000/proceedings.elpub.2018.19http://elpub.episciences.org/4607Pokorny, JanJanPokornyENKI, o.p.s.Automatic Subject Indexing and Classification Using Text Recognition and Computer-Based Analysis of Tables of ContentsThis paper will describe a method for machine-based creation of high quality subject indexing and classification for both electronic and print documents using tables of contents (ToCs). The technology described here is primarily focused on electronic and print documents for which, because of technical or licensing reasons, it is not possible to index full text. However, the technology would also be useful for full text documents, because it could significantly enhance the accuracy and relevance of subject description by analyzing the structure of ToCs.machine learning systemcomputer-generated keywordslibrary automatizationtext miningcomputer-generated subject headings[SHS.INFO]Humanities and Social Sciences/Library and information sciencesAttribution 4.0 International (CC BY 4.0)2018-06-202018-06-202018-06-20engjournal article https://hal.science/hal-01816705v1open accesshttp://elpub.episciences.org/4607/pdfVoRapplication/pdfElPub - ELectronic PUBlishingConnecting the Knowledge Commons: From Projects to Sustainable InfrastructureLong PapersResearchersStudents