Analiza tipa, strukture i učinkovitosti marketinških poruka poslanih metodom elektroničke pošte

master's thesis

• Title (english): Analysis of the type, structure, and effectiveness of e-mail marketing messages
• Author: Martina Galić
• Mentor: Damir Pintar (mentor)
• Committee member: Damir Pintar (predsjednik povjerenstva)
• Committee member: Mihaela Vranić (član povjerenstva)
• Committee member: Luka Humski (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-01, Croatia

Abstract

U sklopu ovog rada istražena je uloga elektroničke pošte kao ključnog alata u marketinškim strategijama suvremenih korporacija. Analizirane su različite vrste marketinških poruka, povijest email marketinga i popularni softveri za email marketing, čime su prikazane brojne mogućnosti koje email marketing nudi. Detaljno je opisana metodologija prikupljanja i obrade podataka, uključujući automatiziranu registraciju uz pomoć Selenium-a te prikupljanje podataka korištenjem IMAP-a i Amazon Web Services (S3). Poseban naglasak stavljen je na kreiranje skupova za treniranje i testiranje, što je omogućilo razvoj preciznog sustava klasifikacije poruka. Analizirani su sustavi temeljeni na pravilima i strojnom učenju, s fokusom na Naive Bayes i BERT modele. Na temelju tih analiza izrađen je alat koji olakšava klasifikaciju i upravljanje marketinškim porukama.

Abstract (english)

This study explores the role of email as a key tool in the marketing strategies of modern corporations. Various types of marketing messages, the history of email marketing, and popular email marketing software are analyzed, highlighting the numerous possibilities offered by email marketing. The methodology for data collection and processing is detailed, including automated registration using Selenium and data collection using IMAP and Amazon Web Services (S3). Special emphasis is placed on creating training and testing datasets, which enabled the development of an accurate message classification system. Classification systems based on rules and machine learning, with a focus on Naive Bayes and BERT models, are analyzed. Based on these analyses, a tool was developed to facilitate the classification and management of marketing messages.

• Keywords: email marketing; marketinške strategije; automatizacija; strojno učenje; BERT; Naive Bayes
• Keywords (english): email marketing; marketing strategies; automation; machine learning; BERT; Naive Bayes
• Language: croatian
• URN:NBN: urn:nbn:hr:168:650404
• 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: 2024-10-12 20:36:35