Annif: DIY automated subject indexing using multiple algorithms

Suominen, Osma

doi:10.18352/lq.10285

Cited by 32 publications

(29 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Annif, an automated subject indexing tool currently being tested and implemented at the National Library of Finland, is also comparable to our approach (Suominen, 2019). Annif annotates terms from different subject vocabularies and thesauri to documents based on textual information, such as abstracts and/or titles.…”

Section: Using Textual Data and Machine Learning To Cluster Or Classify (Social Science) Publicationsmentioning

confidence: 99%

Fine-grained classification of social science journal articles using textual data: A comparison of supervised machine learning approaches

Eykens

Guns

Engels

2021

Quantitative Science Studies

View full text Add to dashboard Cite

We compare two supervised machine learning algorithms—Multinomial Naïve Bayes and Gradient Boosting—to classify social science articles using textual data. The high level of granularity of the classification scheme used and the possibility that multiple categories are assigned to a document make this task challenging. To collect the training data, we query three discipline specific thesauri to retrieve articles corresponding to specialties in the classification. The resulting data set consists of 113,909 records and covers 245 specialties, aggregated into 31 subdisciplines from three disciplines. Experts were consulted to validate the thesauri-based classification. The resulting multilabel data set is used to train the machine learning algorithms in different configurations. We deploy a multilabel classifier chaining model, allowing for an arbitrary number of categories to be assigned to each document. The best results are obtained with Gradient Boosting. The approach does not rely on citation data. It can be applied in settings where such information is not available. We conclude that fine-grained text-based classification of social sciences publications at a subdisciplinary level is a hard task, for humans and machines alike. A combination of human expertise and machine learning is suggested as a way forward to improve the classification of social sciences documents.

show abstract

Section: Using Textual Data and Machine Learning To Cluster Or Classify (Social Science) Publicationsmentioning

confidence: 99%

Fine-grained classification of social science journal articles using textual data: A comparison of supervised machine learning approaches

Eykens

Guns

Engels

2021

Quantitative Science Studies

View full text Add to dashboard Cite

show abstract

“…Sisällönkuvailun avuksi on kehitetty työkaluja, joista yksi on tässä artikkelissa käsiteltävä Annif (Suominen 2019). Annifin toiminta perustuu erilaisiin kieliteknologiaa ja koneoppimista hyödyntäviin työkaluihin ja algoritmeihin, joita voi käyttää erikseen tai yhdessä toistensa kanssa.…”

Section: Automaattisen Sisällönkuvailun Työkalu Annifunclassified

Automaattisen sisällönkuvailun ohjelmiston rakentaminen – case Annif

Lappalainen¹,

Hulkkonen²,

Inkinen³

et al. 2022

Signum

Self Cite

View full text Add to dashboard Cite

Sisällönkuvailun automatisointiratkaisut ovat puhuttaneet kirjastomaailmassa viime vuosina, ja erilaisia kokeiluja on tehty niin Suomessa kuin maailmallakin. Kansalliskirjastossa kehitetty automaattisen sisällönkuvailun Annif-työkalu on herättänyt paljon mielenkiintoa monissa organisaatioissa ja kokemukset ensimmäisistä käyttöönotoista ovat olleet lupaavia. Mitä kehitysvalintoja Annifia rakennettaessa on tehty, ja minkälaisia haasteita kuvailun automatisointiin ylipäätään liittyy?

show abstract

“…1. Automated subject indexing of mathematical library inventories with the toolkit annif [13]. The optimal input format for classifications and vocabularies is a Turtle serialisation.…”

Section: Msc 2020 Skosificationmentioning

confidence: 99%

10 Years Later: The Mathematics Subject Classification and Linked Open Data

Arndt¹,

Ion²,

Runnwerth³

et al. 2021

Preprint

View full text Add to dashboard Cite

Ten years ago, the Mathematics Subject Classification MSC 2010 was released, and a corresponding machine-readable Linked Open Data collection was published using the Simple Knowledge Organization System (SKOS). Now, the new MSC 2020 is out. This paper recaps the last ten years of working on machine-readable MSC data and presents the new machine-readable MSC 2020. We describe the processing required to convert the version of record, as agreed by the editors of zbMATH and Mathematical Reviews, into the Linked Open Data form we call MSC2020-SKOS. The new form includes explicit marking of the changes from 2010 to 2020, some translations of English code descriptions into Chinese, Italian, and Russian, and extra material relating MSC to other mathematics classification efforts. We also outline future potential uses for MSC2020-SKOS in semantic indexing and sketch its embedding in a larger vision of scientific research data.

show abstract

Annif: DIY automated subject indexing using multiple algorithms

Cited by 32 publications

References 10 publications

Fine-grained classification of social science journal articles using textual data: A comparison of supervised machine learning approaches

Fine-grained classification of social science journal articles using textual data: A comparison of supervised machine learning approaches

Automaattisen sisällönkuvailun ohjelmiston rakentaminen – case Annif

10 Years Later: The Mathematics Subject Classification and Linked Open Data

Contact Info

Product

Resources

About