Metode analize teksta u sustavima za potporu korisnicima

master's thesis

• Title (english): Text Analysis Methods for Customer Support Systems
• Author: Ante Šušak
• Mentor: Sven Lončarić (mentor)
• Committee member: Sven Lončarić (predsjednik povjerenstva)
• Committee member: Marko Subašić (član povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Metode analize teksta imaju važnu ulogu u rješavanju problema detekcije semantički jednakih pitanja, čije rješavanje ima izravnu primjenu u sustavima za potporu korisnicima.
U ovom radu taj se problem rješava uz pomoć pristupa zasnovanom na strojnom učenju, gdje se kao značajke koriste rezultati različitih metoda analize teksta.
Kod evaluacije sustava razmatrano je više modela, a najboljim se pokazao model koji koristi
gradient boosting. Opisana je i jednostavna web aplikacija koja koristi implementirani model.

Abstract (english)

Text analysis methods play an important role in solving the problem of detecting semantically equal questions, the solution of which has a direct application in customer support systems. In this thesis, this problem is solved with the help of a machine learning-based approach, where the results of different text analysis methods are used as features. When evaluating the system, several models were considered, and the model using gradient boosting proved to be the best. A simple web application using the implemented model is also described.

• Keywords: analiza teksta; strojno učenje; obrada prirodnog jezika; frekvencija pojma; obrnuta frekvencija dokumenta; vektorizacija riječi; vektorizacija rečenice
• Keywords (english): text analysis; machine learning; natural language processing; term frequency; inverse document frequency; word embedding; sentence embedding
• Language: croatian
• URN:NBN: urn:nbn:hr:168:435401
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 10:49:20