Aplikacija za vježbu pravopisa uz pomoć umjetne inteligencije i usluge strojne provjere pravopisa

master's thesis

• Title (english): Spelling Practice Application Utilizing Artificial Intelligence and machine spell-checking services
• Author: Petar Krešimir Pavičić
• Mentor: Tomislav Jagušt (mentor)
• Committee member: Tomislav Jagušt (predsjednik povjerenstva)
• Committee member: Gordan Gledec (član povjerenstva)
• Committee member: Marko Horvat (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-05, Croatia

Abstract

U današnjem digitalnom dobu, tehnologija ima ključnu ulogu u obrazovanju, posebno u unapređenju jezičnih vještina poput pravopisa. Tradicionalni pristupi u učenju pravopisa često su se oslanjali na memorizaciju pravila i praktičnu primjenu kroz vježbe pisanja. Integracija tehnologije omogućava prilagodljiv pristup učenju i podučavanju, koristeći interaktivne i vanjske alate koji se prilagođavaju potrebama učenika i olakšavaju posao nastavnicima. Ispravi.me se ističe kao napredan alat za... More ispravljanje pravopisnih grešaka, nudeći automatsko i kontekstualno ispravljanje riječi. Ovaj rad istražuje primjenu generativne umjetne inteligencije u obrazovanju, posebno kroz razvoj aplikacije Pravopisnica. Aplikacija je izrađena korištenjem Node.js na backendu i Reacta na frontendu, a za bazu podataka je korišten PostgreSQL, čije prednosti uključuju visoku pouzdanost, skalabilnost i podršku za složene upite, što je ključno za obradu i pohranu podataka korisnika pri rješavanju vježbi. Aplikacija također koristi API-je poput ChatGPT-a za izradu zadataka, ElevenLabs TTS za visokokvalitetnu sintezu teksta u govor, te integrira mogućnosti ispravljanja zadataka putem Ispravi.me API-ja kako bi unaprijedila proces učenja pravopisa. Integracija tehnologije u obrazovni proces omogućava nastavnicima fokus na interakciju s učenicima i pružanje personalizirane podrške, čineći obrazovanje učinkovitijim i pristupačnijim. Kroz ovakve inovativne pristupe, nastavnici se mogu osloboditi rutinskih zadataka ispravljanja i fokusirati se na pružanje personalizirane podrške i feedbacka svojim učenicima. Less

Abstract (english)

In today's digital age, technology plays a key role in education, especially in
improving language skills such as spelling. Traditional approaches to learn spelling have
often relied on memorization of rules and practical application of writing exercises. The
integration of technology enables an adaptive approach to learning and teaching, using
interactive and external tools that adapt to the needs of students and facilitate the work
of teachers. Ispravi.me stands out as an... More advanced tool for correcting spelling errors,
offering automatic and contextual word correction. This paper explores the usage of
generative artificial intelligence in education, especially through the development of the
Pravopisnica application. The application was created using Node.js on the backend and
React on the frontend, and PostgreSQL was used for the database, the advantages of
which include high reliability, scalability and support for complex queries, which is
essential for processing and storing user data when solving exercises. The application also
uses APIs such as ChatGPT for task creation, ElevenLabs TTS for high-quality text-tospeech synthesis, and it integrates task correction capabilities via the Ispravi.me API to
enhance the spelling learning process. Integrating technology into the educational
process allows teachers to focus on interacting with students and providing personalized
support, making education more efficient and accessible. Through such innovative
approaches, teachers can free themselves from routine correction tasks and focus on
providing personalized support and feedback to their students. Less

• Keywords: pravopis; React; Express; Node.js; PostgreSQL; API; Ispravi.me; ChatGPT; ElevenLabs TTS
• Keywords (english): spelling; React; Express; Node.js; PostgreSQL; API; Ispravi.me; ChatGPT; ElevenLabs TTS
• Language: croatian
• URN:NBN: urn:nbn:hr:168:907696
• 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: Open access
• Created on: 2025-02-25 13:37:30