Title Ekspertni sustav za podučavanje japanskog slikovnog pisma kanji Title (english) Expert system for teaching Japanese Kanji characters Author Sara Librenjak Mentor Kristina Kocijan (mentor)Committee member Nives Mikelić Preradović (predsjednik povjerenstva)Committee member Vedran Juričić (član povjerenstva)Committee member Irena Srdanović (član povjerenstva)Granter University of Zagreb Defense date and country 2022-01-21, Croatia Scientific / art field, SOCIAL SCIENCES Universal decimal classificationUDC ) 81 - Linguistics and languages 003 - Writing systems and scripts. Signs and symbols. Codes. Graphic representation Abstract Ova doktorska radnja predstavila je model ekspertnog sustava za optimizaciju redoslijeda podučavanja ili učenja japanskog slikovnog pisma kanji. Ekspertni sustav je sustav baziran na pravilima koji kroz niz pravila i bazu stručnog znanja pomaže krajnjem korisniku u donošenju odluke i pripada u područje umjetne inteligencije. U ovom radu smo predstavili dizajn modela ekspertnog sustava u kojem korisnik unosi parametre vezane za učenje kanji znakova, i kao izlaz dobiva popis znakova primjeren za te parametre. Ulazni parametri su, između ostalog: korišteni udžbenici, broj znakova koje ciljamo, stupanj učenja, stupanj standardiziranog ispita, posebni slučajevi i izostavljeni znakovi. Oni znakovi koji se češće pojavljuju su korisniji da naučiti ranije, jer pokrivaju veći dio teksta i slijede Zipfov zakon. Također, znakovi koji su sastavljeni od kompleksnijih dijelova su teži za zapamtiti nego sami dijelovi. Zato se koriste dva principa optimizacije. Prvo, sustav uzima u obzir princip da dio znaka treba doći prije cjeline kako bi se znak lakše razumio i za to koristi algoritam za topološko sortiranje. Uz to, uzima u obzir učestalost znakova u različitim korpusima, kao što su književni, novinski, Wikipedija i Twitter, kako bi izračunao relativne težine znakova. U radnji smo predstavili nekoliko izlaza sustava, i jedan od njih evaluirali kroz dvosemestralno korištenje na kolegiju u sklopu studija japanskog jezika. Studenti (N = 43) koji su slušali i polagali kolegij u oba semestra su sudjelovali u evaluaciji i ocijenili ovaj redoslijed boljim od redoslijeda u udžbeniku japanskog jezika (3,023 od 5 u odnosu na 4,027 od 5; 72 % ispitanika je slaže ili izrazito slaže da im je redoslijed poboljšao učenje), općenito izrazili zadovoljstvo s ovim načinom učenja (4,476 od 5) i u velikom broju uspješno položili kolegij (77,5 % je završilo oba semestra s ocjenom 4 ili 5; 60% s ocjenom 5). Kroz ovaj model sustava i eksperiment s njegovim rezultatom utvrdili smo da ekspertni sustav ima svoju primjenu i u obrazovanju, odnosno dizajnu kurikuluma i planiranju nastave. Smatramo da primjena ekspertnog sustava u području podučavanja kanji znakova može pomoći profesorima i učenicima da bolje i lakše organiziraju i isplaniraju učenje, i brže postignu željene rezultate.
Abstract (english) In this doctoral thesis, we presented the model of an expert system for teaching or learning Japanese logographic characters kanji. Expert system is a field of artificial intelligence, a rule-based system that helps users in decision-making and consists of an inference engine and a knowledge base. In this thesis, we designed the model of an expert system that helps the user decide the optimal kanji learning order. A user inputs kanji-learning-related parameters and is given a character list as output. The input parameters include a textbook used, goal number of characters, students' level, student's goals, and omitted characters. We learned that the most common kanji in Japanese texts are more useful to know earlier in one's studies because they follow Zipf's law and one is able to understand more characters in text by knowing more frequent characters. In addition to that, many kanji characters are made from components that are characters themselves. It is easier to memorise the parts before the whole, or components before the complex characters. Therefore we used two basic principles in optimisation of learning order. Firstly, the system takes into account the “part before whole” principle and uses an adapted topological sort algorithm. Secondly, it computes the relative weights of characters based on their frequency in corpora, such as literature, newspaper, Wikipedia, and Twitter web corpus. The expert system was evaluated by using one of the system’s output throughout a two-semester study at a university-level Japanese language course. In a kanji-focused module, the students (N ? 43) evaluated the kanji learning order made by the system. Comparing it to the textbook order, they rated it more favourably (3.023 out of 5 compared to 4.027 out of 5) and 72% agreed or strongly agreed that the new order improved their learning process. Additionally, the participants were very happy with this learning method, rating it 4.476 out of 5 on average, and passed the module with high marks (60% of students achieved A+, while 77.5% achieved either A+ or A). Designing the model of this expert system and evaluating it in the practical teaching experiment lead us to believe that expert systems do have a role in education, specifically in curriculum design and class planning. We assert that the application of an expert system in the field of teaching kanji can help both teachers and learners to better organise and plan their learning and achieve desired results quicker.
Keywords
ekspertni sustav
sustavi temeljeni na pravilima
kanji
slikovno pismo
japanski jezik
redoslijed učenja
trošak učenja
primjena ekspertnog sustava u obrazovanju
Keywords (english)
expert system
rule-based systems
kanji
logographic characters
Japanese language
learning order
learning cost
application of expert systems in education
Language croatian DOI https://doi.org/10.17234/diss.2022.203365 URN:NBN urn:nbn:hr:131:063297 Study programme Title: Postgraduate (Doctoral) Program in Information Science Type of resource Text Extent 254 str. File origin Born digital Access conditions Open access Terms of use Created on 2022-03-08 09:50:49
