LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs

This paper presents LYRICEL, a framework integrating Knowledge Graph (KG) representation learning, Large Language Models (LLMs), and machine learning for reliable, explainable, and validatable cross-cultural lyric analysis. The core component, Sequential Language Model Integration (SLMI), enhances t...

Full description

Saved in:
Bibliographic Details
Main Authors: Dimitrios P. Panagoulias, Evangelia-Aikaterini Tsichrintzi, Dionisios N. Sotiropoulos, Konstantina Chrysafiadi, Evangelos Sakkopoulos, George A. Tsihrintzis, Maria Virvou
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11121171/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330033919787008
author Dimitrios P. Panagoulias
Evangelia-Aikaterini Tsichrintzi
Dionisios N. Sotiropoulos
Konstantina Chrysafiadi
Evangelos Sakkopoulos
George A. Tsihrintzis
Maria Virvou
author_facet Dimitrios P. Panagoulias
Evangelia-Aikaterini Tsichrintzi
Dionisios N. Sotiropoulos
Konstantina Chrysafiadi
Evangelos Sakkopoulos
George A. Tsihrintzis
Maria Virvou
author_sort Dimitrios P. Panagoulias
collection DOAJ
description This paper presents LYRICEL, a framework integrating Knowledge Graph (KG) representation learning, Large Language Models (LLMs), and machine learning for reliable, explainable, and validatable cross-cultural lyric analysis. The core component, Sequential Language Model Integration (SLMI), enhances the interpretability and reliability of transformer-based LLMs by addressing explainability and validation challenges through Retrieval-Augmented Generation (RAG), hybrid search, and rule-based evaluation. An important feature of LYRICEL is its use of KG visualizations, which serve as dynamic links to improve interpretability and validatability by structuring data relationships and sources. These visualizations are central to advancements in four areas: KG representation learning, knowledge acquisition, temporal KGs, and knowledge-aware applications. Tested on Greek folk music with models like GPT-4o and BERT, LYRICEL’s trustworthiness is assessed using the VIRTSI model, which quantifies cognitive trust in human-computer interactions. The framework shows strong potential for cross-cultural applications, particularly in languages such as Modern Greek which encompasses a rich cultural heritage spanning centuries of history and traditions resulting in a complex study. The outcomes of GPT-enabled LYRICEL are compared to ChatGPT alone and show a significant improvement in the reliability and efficiency of interactions that can reach a global audience, enhancing the accessibility and understanding of diverse cultural heritages.
format Article
id doaj-art-f51e9d44fc9b4fb582d86361ec1ea064
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-f51e9d44fc9b4fb582d86361ec1ea0642025-08-20T03:47:06ZengIEEEIEEE Access2169-35362025-01-011314198514200610.1109/ACCESS.2025.359721311121171LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek SongsDimitrios P. Panagoulias0https://orcid.org/0000-0002-9421-141XEvangelia-Aikaterini Tsichrintzi1https://orcid.org/0009-0009-3821-1333Dionisios N. Sotiropoulos2Konstantina Chrysafiadi3https://orcid.org/0000-0001-8096-1407Evangelos Sakkopoulos4https://orcid.org/0000-0002-6852-384XGeorge A. Tsihrintzis5https://orcid.org/0000-0002-2716-4035Maria Virvou6https://orcid.org/0000-0002-4008-4654Department of Informatics, University of Piraeus, Piraeus, GreeceDepartment of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, GreeceDepartment of Informatics, University of Piraeus, Piraeus, GreeceDepartment of Informatics, University of Piraeus, Piraeus, GreeceDepartment of Informatics, University of Piraeus, Piraeus, GreeceDepartment of Informatics, University of Piraeus, Piraeus, GreeceDepartment of Informatics, University of Piraeus, Piraeus, GreeceThis paper presents LYRICEL, a framework integrating Knowledge Graph (KG) representation learning, Large Language Models (LLMs), and machine learning for reliable, explainable, and validatable cross-cultural lyric analysis. The core component, Sequential Language Model Integration (SLMI), enhances the interpretability and reliability of transformer-based LLMs by addressing explainability and validation challenges through Retrieval-Augmented Generation (RAG), hybrid search, and rule-based evaluation. An important feature of LYRICEL is its use of KG visualizations, which serve as dynamic links to improve interpretability and validatability by structuring data relationships and sources. These visualizations are central to advancements in four areas: KG representation learning, knowledge acquisition, temporal KGs, and knowledge-aware applications. Tested on Greek folk music with models like GPT-4o and BERT, LYRICEL’s trustworthiness is assessed using the VIRTSI model, which quantifies cognitive trust in human-computer interactions. The framework shows strong potential for cross-cultural applications, particularly in languages such as Modern Greek which encompasses a rich cultural heritage spanning centuries of history and traditions resulting in a complex study. The outcomes of GPT-enabled LYRICEL are compared to ChatGPT alone and show a significant improvement in the reliability and efficiency of interactions that can reach a global audience, enhancing the accessibility and understanding of diverse cultural heritages.https://ieeexplore.ieee.org/document/11121171/ChatGPTLLMse-learningmachine learningartificial intelligencecultural heritage
spellingShingle Dimitrios P. Panagoulias
Evangelia-Aikaterini Tsichrintzi
Dionisios N. Sotiropoulos
Konstantina Chrysafiadi
Evangelos Sakkopoulos
George A. Tsihrintzis
Maria Virvou
LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs
IEEE Access
ChatGPT
LLMs
e-learning
machine learning
artificial intelligence
cultural heritage
title LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs
title_full LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs
title_fullStr LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs
title_full_unstemmed LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs
title_short LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs
title_sort lyricel knowledge graphs combined with large language models and machine learning for cross cultural analysis of lyrics x2014 the case of greek songs
topic ChatGPT
LLMs
e-learning
machine learning
artificial intelligence
cultural heritage
url https://ieeexplore.ieee.org/document/11121171/
work_keys_str_mv AT dimitriosppanagoulias lyricelknowledgegraphscombinedwithlargelanguagemodelsandmachinelearningforcrossculturalanalysisoflyricsx2014thecaseofgreeksongs
AT evangeliaaikaterinitsichrintzi lyricelknowledgegraphscombinedwithlargelanguagemodelsandmachinelearningforcrossculturalanalysisoflyricsx2014thecaseofgreeksongs
AT dionisiosnsotiropoulos lyricelknowledgegraphscombinedwithlargelanguagemodelsandmachinelearningforcrossculturalanalysisoflyricsx2014thecaseofgreeksongs
AT konstantinachrysafiadi lyricelknowledgegraphscombinedwithlargelanguagemodelsandmachinelearningforcrossculturalanalysisoflyricsx2014thecaseofgreeksongs
AT evangelossakkopoulos lyricelknowledgegraphscombinedwithlargelanguagemodelsandmachinelearningforcrossculturalanalysisoflyricsx2014thecaseofgreeksongs
AT georgeatsihrintzis lyricelknowledgegraphscombinedwithlargelanguagemodelsandmachinelearningforcrossculturalanalysisoflyricsx2014thecaseofgreeksongs
AT mariavirvou lyricelknowledgegraphscombinedwithlargelanguagemodelsandmachinelearningforcrossculturalanalysisoflyricsx2014thecaseofgreeksongs