NAPOVEDOVANJE OCEN PRODUKTOV V SPLETNI TRGOVINI Z METODAMI STROJNEGA UČENJA

Gombač, Jošt (author), Todorovski, Ljupčo (mentor)

Razvijalci se pri razvoju in izboljševanju svojih produktov pogosto zanašajo na povratne informacije kupcev. Eden izmed virov teh informacij so spletne trgovine, ki kupcem omogočajo recenziranje in ocenjevanje izdelkov in storitev. Zaradi velikega števila spletnih platform in recenzij pa sta zbiranje in analiza tovrstnih informacij težka in počasna procesa. Pogosto je nemogoče pregledati vse recenzije ali pa se zapletemo v podrobnosti, zaradi česar izgubimo pogled na celotno sliko informacij, ki so jih uporabniki želeli sporočiti. Diplomsko delo obravnava uporabo strojnega učenja pri analizi recenzij uporabnikov spletnih trgovin z namenom napovedovanja številčnih ocen iz besedil recenzij. V povezavi s tem je bila razvita programska rešitev, ki s kombinacijo algoritmov za obdelavo naravnega jezika in metod strojnega učenja napoveduje uporabnikovo oceno. Osrednji cilj raziskave je pridobiti empirični dokaz, da so za nalogo analiziranja besedil v naravnem jeziku in napovedovanja ocene iz njih metode strojnega učenja bolj točne od preprostih analiz sentimenta in statistične obravnave. Rezultati empiričnega preverjanja kažejo na to, da so metode strojnega učenja za izbrano nalogo boljše od preprostih analiz sentimenta s statistično obravnavo glede na več meril za vrednotenje napovedi.

• Language: Slovenian
• Keywords: umetna inteligenca, obdelava naravnega jezika, strojno učenje, klasifikacija, nevronske mreže, odločitvena drevesa, naključni gozdovi, analiza sentimenta
• Work type: Bachelor thesis/paper
• Organization: FU - Faculty of Administration
• Year: 2018
• PID: 20.500.12556/RUL-103188
• Publication date in RUL: 14.09.2018

GOMBAČ, Jošt, 2018, NAPOVEDOVANJE OCEN PRODUKTOV V SPLETNI TRGOVINI Z METODAMI STROJNEGA UČENJA [online]. Bachelor’s thesis. [Accessed 1 April 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=103188

Secondary language

• Language: English
• Title: PREDICTING PRODUCT RATINGS IN A WEB STORE WITH MACHINE LEARNING METHODS

Abstract

Product developers often rely on customer feedback when developing and improving their products. One source of such feedback are Web stores that enable customers to review and rate products and services. Given the large number of Web stores and reviews, the process of gathering and analyzing the feedback information is usually tedious and slow. It is often impossible to examine all the available reviews and the results of their analysis provides us with too much details. The later derails us from seeing the big picture or the main message of feedback that customers wanted to communicate with us. The thesis applies machine learning methods to the task of processing customer reviews available in the Web stores with a purpose of giving predictions of their corresponding numerical ratings. In particular, we developed a solution that combines natural language processing algorithms with machine learning methods to predict customer ratings. The central thesis goal is to empirically prove that machine learning methods are more accurate than simple sentiment analysis and statistical methods when predicting customer ratings from natural language reviews. Results of empirical evaluation show that on the selected prediction task machine learning methods perform better than simple sentiment analysis and statistical treatment with respect to multiple evaluation metrics.

• Keywords: artificial intelligence, natural language processing, machine learning, classification, neural networks, decision trees, random forest, sentiment analysis