Preporučiteljski sustav zasnovan na podacima o interakciji na Facebooku

undergraduate thesis

• Title (english): Recommender system based on data about interaction on Facebook
• Author: Domagoj Hrestak
• Mentor: Marko Banek (mentor)
• Committee member: Marko Banek (predsjednik povjerenstva)
• Committee member: Boris Vrdoljak (član povjerenstva)
• Committee member: Damir Pintar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-09-02, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U završnom radu obrađena je tema preporučiteljskih sustava. Opisane su vrste sustava te prednosti njihove upotrebe na društvenim mrežama. Fokus je bio na društvenoj mreži Facebook i njihovoj platformi za razvoj aplikacija. Nakon definiranja korištenih tehnologija platforme dotakli smo se općenite politike razvoja aplikacija na toj brzorastućoj društvenoj platformi gdje su spomenuti i nedostaci trenutne verzije platforme te najveće promjene u odnosu na prijašnje inačice. Objašnjeni su korišteni pojmovi i tehnologije uz kratak osvrt na općenite informacije vezane uz MVC arhitekturu, ASP.NET, Facebook SDK za .NET, JSON.NET, Bootstrap i ostale korištene radne okvire. U zadnjem poglavlju nalazi se osvrt na postavljanje postavki Facebook platna i aplikacije te općenitih uputa za Microsoft Azure profil. Slijedi detaljan opis sagrađenog sustava i svih slojeva aplikacije. Opisan je algoritam za analizu interakcije korisnika i pripadni modeli za spremanje podataka. Konačno, demonstriran je tipičan scenarij korištenja aplikacije za preporučivanje sadržaja.

Abstract (english)

This bachelor thesis is about recommender systems and their development on social networks like Facebook. We have defined the most common types of recommender systems and their advantages and disadvantages. The main theme of this thesis is developing a recommender system using the Facebook platform. After defining the technologies used in the project we discuss some general Facebook policies on application development and the flaws of the current version concerning new privacy settings and limited access to data. Further on we explain the used technologies and give some common information and explanations about the MVC software architectural pattern, ASP.NET, Facebook SDK for .NET, JSON.NET, Bootstrap and the rest of the used frameworks. Last chapter contains recapitulation about using and setting up the Facebook Canvas frame with a web application and usage information for the Microsoft Azure cloud. Detailed descriptions of the developed recommender system and all the implemented layers follow. The algorithm used to analyse the Facebook interaction data is explained and so are the related model data structures. Finally, a demonstration of the developed recommender system is given through a typical use case scenario.

• Keywords: Preporučiteljski sustav; web aplikacija; Facebook Graph API; ASP.NET MVC; Facebook SDK za .NET; Microsoft Azure
• Keywords (english): Recommender system; web application; Facebook Graph API; ASP.NET MVC; Facebook SDK for .NET; Microsoft Azure
• Language: croatian
• URN:NBN: urn:nbn:hr:168:283235
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 09:12:09