izpis_h1_title_alt

Sistem za priporočanje in implementacija na primeru spletne platforme Twitch : diplomsko delo
Tomšič, Gašper (Author), Škulj, Damjan (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (1,47 MB)

Abstract
Podatki imajo pomembno vlogo za delovanje in organiziranje naše družbe, vendar se v zadnjem desetletju soočamo s težavo prevelike količine podatkov. Eden izmed načinov reševanja te težave so sistemi za priporočanje. To so sistemi, ki poskušajo iz množice podatkov posamezniku priporočati njemu najbolj zanimive in relevantne podatke. Tak pristop se pogosto uporablja na spletu. Cilj diplomskega dela je opisati področje sistemov za priporočanje in na primeru spletne platforme Twitch ugotoviti, ali je možno posamezniku predlagati vsebino glede na izbiro vsebine posamezniku podobnih uporabnikov. Twitch je spletna platforma za predvajanje vsebin v živo. Zaradi ogromne količine video vsebin posameznik ni zmožen izbrati sebi najbolj primerne vsebine. Ustvarili smo štiri modele za priporočanje po metodi najbližjih sosedov. Dva po iskanju najbližjih uporabnikov, kjer smo za mero podobnosti uporabili Jaccardovo podobnost in kosinus podobnosti, in dva po iskanju najbližjih kanalov z istimi merami podobnosti. Najbolj natančen model je bil priporočanje po podobnosti uporabnikov s kosinusom podobnosti. Naš model smo primerjali s priporočanjem po naključju in popularnosti. Končni rezultat je bil, da je priporočanje s primerjanjem uporabnikov in kanalov bolj natančno od naključja in popularnosti. Potrdili smo hipotezo, da je možno uporabniku priporočati vsebino glede na izbiro vsebine njemu podobnih uporabnikov.

Language:Slovenian
Keywords:sistem za priporočanje, metoda najbližjih sosedov, Twitch
Work type:Bachelor thesis/paper (mb11)
Tipology:2.11 - Undergraduate Thesis
Organization:FDV - Faculty of Social Sciences
Year:2020
Publisher:[G. Tomšič]
Number of pages:41 str.
UDC:004.93(043.2)
COBISS.SI-ID:26653187 Link is opened in a new window
Views:130
Downloads:43
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Recommender system and an implementation on the online platform Twitch
Abstract:
Data plays a big role in operation and organization of our society. However, in the last decade we are facing an issue of excessive amount of data. One way to solve this problem are recommender systems. Recommender systems are systems that try to recommend the most interesting and relevant data to an individual from a mass of data. It is an approach commonly used on the web. The aim of the diploma thesis is to describe the field of recommender system and, using the case of Twitch platform, to determine whether it is possible to recommend content to an individual based on the content consumed by users similar to the individual. Twitch is a live streaming web platform. Due to the enormous amount of video content on Twitch, an individual is not able to choose the most suitable content for himself. We created four models for recommendation using the nearest neighbours method. Two of the models are based on finding the nearest neighbour users according to the Jaccard similarity and the cosine similarity and another two based on finding the nearest channel with the same two similarities. The most accurate model was recommendation based on nearest neighbour users with cosine similarity. We compared our model with recommendations by chance and popularity. The final finding was that the recommendation by comparing the users and channel was more accurate than the recommendations based on chance and popularity. We confirmed the hypothesis that it is possible to recommend content to a user based on the choice of content of similar users.

Keywords:Recommender system, nearest neighbour method, Twitch

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back