Prepoznavanje pristupa programiranju iz blokovskog programskog jezika

master's thesis

• Title (english): Identifying Programming Approaches From Visual Programming Language
• Author: Marin Mrčela
• Mentor: Ana Sović Kržić (mentor)
• Committee member: Ana Sović Kržić (predsjednik povjerenstva)
• Committee member: Juraj Petrović (član povjerenstva)
• Committee member: Tomislav Jagušt (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-02-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Temelj su ovog rada radionice s edukacijskim robotima Lego Spike s kojih su prikupljeni podatci o postupcima rješavanja zadataka. Podatci su zatim obrađeni predstavljenim postupkom pretvorbe rješenja u tekstni ekvivalent. Rezultat obrade se zatim koristi za prikupljanje značajki radionice po učenicima i za automatsko ocjenjivanje rješenja. Promatra se utjecaj teksta zadatka na rješenja i česte pogreške u rješavanju. Prikupljene značajke se zatim koriste kao ulazni podatci u modelima nenadziranog strojnog učenja s ciljem određivanja grupa učenika povezanih zajedničkim značajkama. Grupama se naposlijetku pridružuju opisi na temelju rezultata analize grupa iz sličnih radova.

Abstract (english)

This work is based on workshops using Lego Spike educational robots, from which data on problem-solving methods were gathered. The data was then processed using a presented method that converts solutions into text. This processed information was used to identify characteristics of the workshop for each student and for automatic evaluation of their solutions. The study examines the influence of the task text on the solutions and common mistakes made in solving them. The collected characteristics were used as input for unsupervised machine learning models to identify groups of students with similar traits. Finally, descriptions were assigned to these groups based on analysis from the similar works.

• Keywords: edukacijski roboti; radionice; prikupljanje značajki; analiza teksta; automatsko ocjenjivanje; grupiranje podataka
• Keywords (english): educational robots; workshops; feature collection; text analysis; automatic evaluation; data clustering
• Language: croatian
• URN:NBN: urn:nbn:hr:168:716674
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-07-13 10:23:32