Automatic Subject Indexing and Classification Using Text Recognition and Computer-Based Analysis of Tables of Contents

Jan Pokorny (1)

1 ENKI, o.p.s.

This 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.

Mots clés: machine learning system; computer-generated keywords; library automatization; text mining; computer-generated subject headings

Domaines: Sciences de l'information et de la communication

Jan Pokorny. Automatic Subject Indexing and Classification Using Text Recognition and Computer-Based Analysis of Tables of Contents. ELPUB 2018, Jun 2018, Toronto, Canada. ⟨10.4000/proceedings.elpub.2018.19⟩. ⟨hal-01816705⟩