DC FieldValueLanguage
dc.contributor.advisorTriantafyllou, Ioannis-
dc.contributor.authorΔρίζης, Ιωάννης-
dc.date.accessioned2023-10-13T06:36:41Z-
dc.date.available2023-10-13T06:36:41Z-
dc.date.issued2022-07-08-
dc.identifier.urihttps://uniwacris.uniwa.gr/handle/3000/295-
dc.description.abstractThe Classical Machine Learning and Deep Learning models are used to provide solutions in everyday technologies, like weather prediction, stock price prediction, voice-to-text conversion, fraud detection, quality assurance, etc. These implementations are only a part of a broad range of applications where these algorithms can offer unique services. In this dissertation, Classical Machine Learning models will be compared with Deep Learning Neural Network models, within the frame of Text Classification. This comparison will be done by using three different feature selection metrics, namely tf.idf, chi square (x2) and devmax.tf. Also, different Neural Network Deep Learning architectures are tested and compared between them, as well as different parameters (input vector size, topology architecture, etc.), which are applied in Neural Networks.-
dc.format.extent63-
dc.language.isoen-
dc.publisherUniversity of West Attica (UNIWA)-
dc.rightsΑναφορά Δημιουργού - Μη Εμπορική Χρήση - Παρόμοια Διανομή 4.0 Διεθνές-
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Διεθνές-
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Διεθνές-
dc.subjectMachine learning-
dc.subjectDeep learning-
dc.subjectText preprocessing-
dc.subjectText classification-
dc.subjectDevmax.df-
dc.subjectΜηχανική μάθηση-
dc.subjectΒαθιά μηχανική μάθηση-
dc.subjectΠροεπεξεργασία κειμένων-
dc.subjectΚατηγοριοποίηση κειμένων-
dc.titleDeep-Learning vs Classical Machine-Learning comparison for text classification-
dc.typeMSc Thesis-
dc.relation.deptDepartment of Archival, Library and Information Studies-
dc.relation.facultySchool of Administrative, Economics and Social Sciences-
dc.relation.programΜεταπτυχιακές διπλωματικές εργασίες ΠΜΣ Διαχείριση Πληροφοριών σε Βιβλιοθήκες, Αρχεία, Μουσεία-
dc.contributor.committeememberKouis, Dimitrios-
dc.linkhttp://dx.doi.org/10.26265/polynoe-2355-
item.fulltextNo Fulltext-
item.grantfulltextnone-
item.openairetypeMSc Thesis-
item.languageiso639-1en-
item.cerifentitytypePublications-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
crisitem.author.deptDepartment of Archival, Library and Information Studies-
crisitem.author.facultySchool of Administrative, Economics and Social Sciences-
crisitem.author.orcid0000-0001-5273-0855-
crisitem.author.parentorgSchool of Administrative, Economics and Social Sciences-
Appears in Collections:Master Theses / Μεταπτυχιακές Εργασίες
CORE Recommender
Show simple item record

Page view(s)

17
checked on Nov 23, 2024

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.