Knowledge Graph Embeddings for News Article Tag Recommendation

Nora Engleitner; Werner Kreiner; Nicole Schwarz; Theodorich Kopetzky; Lisa Ehrlinger

Knowledge Graph Embeddings for News Article Tag Recommendation

Nora Engleitner, Werner Kreiner, Nicole Schwarz, Theodorich Kopetzky, Lisa Ehrlinger

Institute for Application-oriented Knowledge Processing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

Newsadoo is a media startup that provides news articles from different sources on a single platform. Users can create individual timelines, where they follow the latest development of a specific topic. To support the topic creation process, we developed an algorithm that automatically suggests related tags to a set of given reference tags. In this paper, we first introduce the Newsadoo tag recommendation system, which consists of three components: (1) item-based similarity, (2) knowledge graph similarity, and (3) actuality. We describe the knowledge graph component in more detail and analyze the suitability of different knowledge graphs and embedding techniques to enhance the quality of the overall Newsadoo tag recommendation. The paper concludes with a list of lessons learned and interesting future work.

Original language	English
Title of host publication	Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins
Editors	Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer
Place of Publication	Aachen
Publisher	Sun SITE Central Europe
Number of pages	5
Volume	2941
Publication status	Published - Sept 2021

Publication series

Name	CEUR Workshop Proceedings

Fields of science

102001 Artificial intelligence
102010 Database systems
102014 Information design
102015 Information systems
102019 Machine learning
102028 Knowledge engineering
102033 Data mining
102035 Data science
509018 Knowledge management

JKU Focus areas

Digital Transformation

Cite this

Engleitner, N., Kreiner, W., Schwarz, N., Kopetzky, T., & Ehrlinger, L. (2021). Knowledge Graph Embeddings for News Article Tag Recommendation. In Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer (Ed.), Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins (Vol. 2941). (CEUR Workshop Proceedings). Sun SITE Central Europe.

Engleitner, Nora ; Kreiner, Werner ; Schwarz, Nicole et al. / Knowledge Graph Embeddings for News Article Tag Recommendation. Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins. editor / Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer. Vol. 2941 Aachen : Sun SITE Central Europe, 2021. (CEUR Workshop Proceedings).

@inproceedings{56cafaa8ac824a54924b4dddaef0c0bf,

title = "Knowledge Graph Embeddings for News Article Tag Recommendation",

abstract = "Newsadoo is a media startup that provides news articles from different sources on a single platform. Users can create individual timelines, where they follow the latest development of a specific topic. To support the topic creation process, we developed an algorithm that automatically suggests related tags to a set of given reference tags. In this paper, we first introduce the Newsadoo tag recommendation system, which consists of three components: (1) item-based similarity, (2) knowledge graph similarity, and (3) actuality. We describe the knowledge graph component in more detail and analyze the suitability of different knowledge graphs and embedding techniques to enhance the quality of the overall Newsadoo tag recommendation. The paper concludes with a list of lessons learned and interesting future work.",

author = "Nora Engleitner and Werner Kreiner and Nicole Schwarz and Theodorich Kopetzky and Lisa Ehrlinger",

year = "2021",

month = sep,

language = "English",

volume = "2941",

series = "CEUR Workshop Proceedings",

publisher = "Sun SITE Central Europe",

editor = "{Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer}",

booktitle = "Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins",

}

Engleitner, N, Kreiner, W, Schwarz, N, Kopetzky, T & Ehrlinger, L 2021, Knowledge Graph Embeddings for News Article Tag Recommendation. in Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer (ed.), Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins. vol. 2941, CEUR Workshop Proceedings, Sun SITE Central Europe, Aachen.

Knowledge Graph Embeddings for News Article Tag Recommendation. / Engleitner, Nora; Kreiner, Werner; Schwarz, Nicole et al.
Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins. ed. / Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer. Vol. 2941 Aachen: Sun SITE Central Europe, 2021. (CEUR Workshop Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

TY - GEN

T1 - Knowledge Graph Embeddings for News Article Tag Recommendation

AU - Engleitner, Nora

AU - Kreiner, Werner

AU - Schwarz, Nicole

AU - Kopetzky, Theodorich

AU - Ehrlinger, Lisa

PY - 2021/9

Y1 - 2021/9

N2 - Newsadoo is a media startup that provides news articles from different sources on a single platform. Users can create individual timelines, where they follow the latest development of a specific topic. To support the topic creation process, we developed an algorithm that automatically suggests related tags to a set of given reference tags. In this paper, we first introduce the Newsadoo tag recommendation system, which consists of three components: (1) item-based similarity, (2) knowledge graph similarity, and (3) actuality. We describe the knowledge graph component in more detail and analyze the suitability of different knowledge graphs and embedding techniques to enhance the quality of the overall Newsadoo tag recommendation. The paper concludes with a list of lessons learned and interesting future work.

AB - Newsadoo is a media startup that provides news articles from different sources on a single platform. Users can create individual timelines, where they follow the latest development of a specific topic. To support the topic creation process, we developed an algorithm that automatically suggests related tags to a set of given reference tags. In this paper, we first introduce the Newsadoo tag recommendation system, which consists of three components: (1) item-based similarity, (2) knowledge graph similarity, and (3) actuality. We describe the knowledge graph component in more detail and analyze the suitability of different knowledge graphs and embedding techniques to enhance the quality of the overall Newsadoo tag recommendation. The paper concludes with a list of lessons learned and interesting future work.

UR - http://ceur-ws.org/Vol-2941/

M3 - Conference proceedings

VL - 2941

T3 - CEUR Workshop Proceedings

BT - Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins

A2 - Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer, null

PB - Sun SITE Central Europe

CY - Aachen

ER -

Engleitner N, Kreiner W, Schwarz N, Kopetzky T, Ehrlinger L. Knowledge Graph Embeddings for News Article Tag Recommendation. In Ilaria Tiddi, Maria Maleshkova, Tassilo Pellegrini, Victor de Boer, editor, Joint Proceedings of the Semantics co-located events: Poster&Demo track and Workshop on Ontology-Driven Conceptual Modelling of Digital Twins. Vol. 2941. Aachen: Sun SITE Central Europe. 2021. (CEUR Workshop Proceedings).

Knowledge Graph Embeddings for News Article Tag Recommendation

Abstract

Publication series

Fields of science

JKU Focus areas

Other files and links

DasRes 2 - Data Analysis Systems

Cite this

Knowledge Graph Embeddings for News Article Tag Recommendation

Abstract

Publication series

Fields of science

JKU Focus areas

Other files and links

Projects

DasRes 2 - Data Analysis Systems

Cite this