Custom Glial Network Architectures for the Classification of Large Text Corpora: A Case Study of Complaint Analysis in the Polish State Railways

StatusVoR
Simple item page
dc.abstract.enWe employ a custom-designed convolutional-glial network architecture for the classification of large text corpora. The problem selected to demonstrate the high effectiveness of the proposed technique, was defined in collaboration with Poland’s largest railway operator. The task involves categorizing incoming reports (submitted by passengers, station staff, and railway line personnel) into appropriate departments based on their textual content. The input data consists of short texts containing complaints, inquiries, and remarks, which were transformed into vector representations using the BERT language model. A hybrid convolutional architecture was then applied, augmented with a glial-type control module that dynamically regulates the activation levels of CNN filters. This glial control layer, inspired by biological mechanisms, was trained alternately with the convolutional component, enabling better adaptation of information flow within the network. Experimental results confirm that this approach outperforms classic architectures in terms of classification accuracy, while also offering greater flexibility and development potential. The proposed solution can be effectively applied in customer service support systems and automated text analysis for public transportation.
dc.affiliationWydział Projektowania w Warszawie
dc.conferenceArtificial Intelligence and Soft Computing 24th International Conference, ICAISC 2025, Zakopane, Poland, June 22–26, 2025, Proceedings, Part I Conference proceedings © 2026
dc.conference.countryPolska
dc.conference.datefinish2025-06-26
dc.conference.datestart2025-06-22
dc.conference.placeZakopane
dc.conference.seriesInternational Conference on Artificial Intelligence and Soft Computing
dc.conference.seriesshortcutICAISC
dc.conference.seriesweblinkhttps://icaisc.eu/
dc.conference.shortcutThe 24th International Conference on Artificial Intelligence and Soft Computing
dc.conference.weblinkhttps://icaisc2025.icaisc.eu/
dc.contributor.authorNowak, Jakub
dc.contributor.authorKrumholc, Tymoteusz
dc.contributor.authorMilewski, Jakub
dc.contributor.authorMaćkiewicz, Aneta
dc.contributor.authorStachowiak, Sylwia
dc.contributor.authorKorytkowski, Marcin
dc.contributor.authorScherer, Rafał
dc.contributor.editorRutkowski, Leszek
dc.contributor.editorScherer, Rafał
dc.contributor.editorKorytkowski, Marcin
dc.contributor.editorPedrycz, Witold
dc.contributor.editorTadeusiewicz, Ryszard
dc.contributor.editorZurada, Jacek M.
dc.date.access2025-10-31
dc.date.accessioned2025-11-13T16:44:52Z
dc.date.available2025-11-13T16:44:52Z
dc.date.created2025-11-12
dc.date.issued2025-11-01
dc.description.accesstimeat_publication
dc.description.physical170-181
dc.description.sdgIndustryInnovationAndInfrastructure
dc.description.sdgSustainableCitiesAndCommunities
dc.description.seriesLecture Notes in Computer Science
dc.description.seriesnumber15948
dc.description.versionfinal_published
dc.description.volume1
dc.identifier.doi10.1007/978-3-032-03705-3_15
dc.identifier.isbn978-3-032-03704-6
dc.identifier.seriesissn0302-9743
dc.identifier.urihttps://share.swps.edu.pl/handle/swps/1987
dc.identifier.weblinkhttps://link.springer.com/chapter/10.1007/978-3-032-03705-3_15
dc.languageen
dc.pbn.affiliationinformatyka techniczna i telekomunikacja
dc.publisher.ministerialSpringer Nature
dc.relation.bookArtificial Intelligence and Soft Computing: 24th International Conference, ICAISC 2025, Zakopane, Poland, June 22–26, 2025, Proceedings, Part I
dc.relation.languageen
dc.relation.pages306
dc.rightsClosedAccess
dc.rights.explanationZa paywallem
dc.rights.questionNo_rights
dc.share.monoPUBLISHER_WEBSITE
dc.swps.sciencecloudsend
dc.titleCustom Glial Network Architectures for the Classification of Large Text Corpora: A Case Study of Complaint Analysis in the Polish State Railways
dc.typeMonographyChapterConference
dspace.entity.typeBook