Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Agder University Res...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 2 versions
addClaim

Generativ kunstig intelligens som støtte for minoritetsspråklige elevers leseforståelse: En aksjonsforskningsstudie i norskdidaktikk

Authors: Sivertsen, Silje Mariell Bauge; Odor, Jelena;

Generativ kunstig intelligens som støtte for minoritetsspråklige elevers leseforståelse: En aksjonsforskningsstudie i norskdidaktikk

Abstract

Sammendrag: Hvordan kan generativ kunstig intelligens brukes som et redskap for elevers lesing i skolen? Gjennom et kvalitativt aksjonsforskningsdesign undersøker denne masteroppgaven hvordan et undervisningsforløp med en tilpasset praterobot kan støtte minoritetsspråklige elevers leseforståelse. Datamaterialet består av praterobotlogger, observasjonsnotater, skjermfilmer og transkripsjoner. I perioden februar-mars 2025 gjennomførte fire elever fra tre ulike ungdomsskoler et nøye planlagt undervisningsforløp. Elevene fikk én klokketime til å lese et tekstutdrag og deretter samhandle med en tilpasset praterobot om tekstens innhold og gi sin evaluering. Prateroboten, som var basert på språkmodellen GPT-4o mini, ble instruert til å innta rollen som en interaktiv læringsassistent med mål om å støtte elevenes forståelse ved å generere innhold basert på deres angitte språk og tekstens kontekst. Elevene evaluerte prateroboten som et godt verktøy. Gjennomgangen i masteroppgaven viser at den tilpassede prateroboten forklarte sentrale ord og begreper på flere språk, samt tydeliggjorde metaforer og tematikk gjennom tolkningsbaserte svar ut fra tekstens kontekst. Dette indikerer at prateroboter som er satt opp på denne måten kan støtte minoritetsspråklige elever til å finne fram til implisitt og eksplisitt tekstinnhold i lesing på andrespråket. Samtidig viser masteroppgaven at praterobotens hjelpsomhet og dens manglende kjennskap til elevenes ferdighetsnivå kan begrense den individuelle støtten og elevers egen refleksjonsevne i møte med tekster. Det er derfor viktig å være bevisst på både begrensninger og muligheter dersom en tilpasset praterobot skal fungere som støtte for minoritetsspråklige elevers leseforståelse, noe denne masteroppgaven adresserer. Nøkkelord: Generativ kunstig intelligens, prateroboter, lesing, leseforståelse, minoritetsspråklige elever og andrespråk. Abstract: How can generative artificial intelligence be used as a helpful tool for pupils` reading in school? Using a qualitative action research design, this master thesis investigates how a lesson plan involving a tailored chatbot can support reading comprehension among L2 learners. The data consist of chatbot logs, observation, screen recordings and transcriptions. During February-March 2025, four pupils from three different middle schools in Norway participated in a carefully planned lesson plan. The pupils were given one hour to read a text, interact with a tailored chatbot about the text content, and then give their evaluation of the experience. The chatbot was based on the GPT-4o mini and was prompted to act as an interactive learning assistant, to support pupils` comprehension by generating responses based on their language and the text`s context. The pupils evaluated the chatbot as a helpful tool. This thesis shows that the chatbot helped explain words and concepts in multiple languages and clarified metaphors and themes through interpretative responses rooted in the text`s context. This indicates that chatbots designed in this manner can support L2 readers in identifying implicit and explicit content. However, the thesis also highlights limitations, such as the chatbots lack of knowledge about individual skill level and its over-assisting tendency, which may reduce opportunities for individual support and pupils’ reflection ability. It is therefore crucial to be aware of both the opportunities and limitations if a tailored chatbot is to be implemented as support for pupils reading comprehension, which is something this thesis addresses. Keywords: Generative artificial intelligence, chatbots, reading, reading comprehension, L2 learners and second language.

Country
Norway
Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green
Related to Research communities