prikaz prve stranice dokumenta Strojno učenje u analizi korisničkih anketa
  Download
PDF 1.42 MB
master's thesis
Strojno učenje u analizi korisničkih anketa
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. urn:nbn:hr:200:432356
Vurnek, Marko
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Vurnek, M. (2021). Strojno učenje u analizi korisničkih anketa (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:432356

Vurnek, Marko. "Strojno učenje u analizi korisničkih anketa." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:432356

Vurnek, Marko. "Strojno učenje u analizi korisničkih anketa." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:432356

Vurnek, M. (2021). 'Strojno učenje u analizi korisničkih anketa', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 25 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:432356

Vurnek M. Strojno učenje u analizi korisničkih anketa [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2021 [cited 2024 April 25] Available at: https://urn.nsk.hr/urn:nbn:hr:200:432356

M. Vurnek, "Strojno učenje u analizi korisničkih anketa", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:200:432356

Metadata
TitleStrojno učenje u analizi korisničkih anketa
Title (english)Machine learning in customer survey analysis
AuthorMarko Vurnek
MentorAlfonzo Baumgartner (mentor)
Committee memberAlfonzo Baumgartner (predsjednik povjerenstva)
Committee memberTomislav Keser (član povjerenstva)
Committee memberTomislav Galba (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2021-06-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Information Systems
Abstract
U ovom radu dan je pregled trenutno aktualnih metoda strojnog učenja za analizu tekstualnih dokumenata. Prikazane su sve faze prirodnog procesiranja jezika kao i različiti algoritmi za klasifikaciju kao što je logistička regresija, Naive Bayes te strojevi s potpornim vektorima. U svrhu demonstracije implementiran je sustav u kojemu korisnici razmjenjuju poruke u stvarnom vremenu pri ćemu se poruke klasificiraju kao pozitivne ili negativne. Pri implementaciji sustava koristio se Apache Spark za izvršavanja svih faza podatkovne pipe za obradu teksta, Node.js i Socket.io za razmjenu poruka u stvarnom vremenu, Apache Kafka za prosljeđivanje poruka sa Node servera na Spark platformu te Apache Cassandra za spremanje rezultata. Također je izvršena evaluacija preciznosti prethodno navedenih algoritama za klasifikaciju pri kojoj su se koristili testni podatci. Poruke se uspješno klasificiraju te prikazana je jednostavna vizualizacija klasificiranih poruka.
Abstract (english)
This paper provides an overview of current machine learning methods for textual document analysis. All phases of natural language processing are presented as well as various classification algorithms such as logistic regression, Naive Bayes and support vector machines. For the purpose of demonstration, a system has been implemented in which users exchanges messages in real time, whereby messages are classified as positive or negative. The system was implemented using Apache Spark to execute all phases of natural languge processing pipeline, Node.js and Socket.io for real-time messaging, Apache Kafka for forwarding messages from the Node server to the Spark platform and Apache Cassandra for saving results. An evaluation of the accuracy of the aforementioned classification algorithms using test data was also performed. Messages are successfully classified and a simple visualization of classified messages is shown.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:432356
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2021-08-16 09:37:16