ArticlePDF Available

Selbstlernphasen mit KI Chatbots - kann das gelingen?

Authors:
Benedikt Brünner at Graz University of Technology
Benedikt Brünner
Martin Ebner at Graz University of Technology
Martin Ebner
Download full-text PDF
Read full-text
Download citation

Abstract

Unsere Hochschule ist ein Ort der Vielfalt und Heterogenität. Bezüglich der Diversität beim Vorwissen unserer Studienanfänger:innen spielen Individualisierung und gezielte Förderung eine wichtige Rolle. In diesem Beitrag geben wir Einblick in die Implementierung eines generativen KI (genKI) Chatbots für Studienanfänger:innen im Fachbereich Informatik an der TU Graz.
Content uploaded by Martin Ebner
Author content
All content in this area was uploaded by Martin Ebner on Mar 23, 2025
Content may be subject to copyright.
!"#$%&'('()&(*)+",(('"-)+.-)!/('"-)0.)123245)6'7/#87'"(9%:#'();&8)<=)>%:8/?8#)@)A:(()
B:#)C'7&(C'(D)E(;:);:C:F&()3GH2324.)6.)GGIGJ.)
%889#*HHKKK.E(;:.:8H$?(8'(8HB?K(7?:BHJGLMH23LJ4DN'"#&?(OJ
)
)
Selbstlernphasen mit KI Chatbots - kann das gelingen?
)
Ein Beitrag von Benedikt Brünner und Martin Ebner, TU Graz
)
Benedikt Brünner, MEd BEd
Benedikt
Brünner
ist Universitätsassistent an der Technischen Universität Graz im
Forschungsbereich der Bildungstechnologie. Er ist Teil des Forschungsprojekts Future of
Digital Education and Learning (FutureDEAL)
Priv.-Doz. Dipl.-Ing. Dr.techn. Martin Ebner
Martin Ebner ist Leiter der Organisationseinheit Lehr- und Lerntechnologien an der
Technischen Universität Graz und damit verantwortlich für alle universitätsweiten E-
Learning-Aktivitäten. Er hat die Lehrbefugnis für Medieninformatik (Schwerpunkt:
Bildungsinformatik)
)
Zusammenfassung:
Unsere Hochschule ist ein Ort der Vielfalt und Heterogenität. Bezüglich der Diversität
beim Vorwissen unserer Studienanfänger:innen spielen Individualisierung und gezielte
Förderung eine wichtige Rolle. In diesem Beitrag geben wir Einblick in die
Implementierung eines generativen KI (genKI) Chatbots für Studienanfänger:innen im
Fachbereich Informatik an der TU Graz.
)
)
P'")0QQ>)=(E?";:8&AIR&8):SE)&0??T.:8)&#8):7#)6'7/#87'"(AS"#)A?(F&9&'"8-)S;):S#C'KU%78')
V"S(B7:C'()B'")P:8'(N'":"/'&8S(C-)W7C?"&8%;&A-)X"?C":;;&'"S(C)S(B)Y'8FK'"A')FS)
N'";&88'7(.)+'C7'&8'(B)B:FS)C&/8)'#):()B'")Z[)V":F)E,"):77')68SB&'"'(B'()'&()E"'&'#)
\:%7E:$%)/'"'&8#)N?")B';)68SB&'(#8:"8)N?()6'98';/'")/&#)W(E:(C)QA8?/'".)P&')=B'')
%&(8'")B&'#';)+",$A'(AS"#*)P'()!&(#8&'C)&()'&()68SB&S;):S#)B';)+'"'&$%)B'")=(E?";:8&A)
FS)'"7'&$%8'"(.)P:FS)#'8F'()K&"):SE)'&()+7'(B'BI0QQ>I]'"(E?";:8)1Z[)V":F)]'%"I)S(B)
]'"(8'$%(?7?C&'(-)232^5-)S;)B&'#')X'"#?('(C"S99')C'F&'78):(FS#9"'$%'(*)!&(&C')
68SB&'"'(B')#&(B)&;)6'98';/'")FS)+'C&(()&%"'#)('S'()]'/'(#:/#$%(&88#)(?$%)(&$%8)&()
V":F.
)
)
=()B&'#';)P&#8:($'I]':"(&(CI6'88&(C)/":S$%8)'#):/'")'&('()CS8'()0&_):S#)=(%:78'()&;)
0QQ>-)N'"8&'E'(B'()`/S(C'(-)'a'A8&N')<?;;S(&A:8&?(-)#b($%"?(')%b/"&B')
]'"('&(%'&8'(-):/'"):S$%)<?;9'8'(F'()E,")#'7/#8"'CS7&'"8'#)]'"('()1+",(('")'8):7.-)
232^5.)=;)c:%")232^)%:/'()K&")B&'#'()0&_)FS#U8F7&$%);&8)'&(';)>%:8/?8)'"K'&8'"8-)B'")&;)
d?"E'7B);&8):77'()=(%:78'():SE/'"'&8'8)KS"B'-)S;)eS:7&8:8&N)%?$%K'"8&C')W(8K?"8'()C'/'()
FS)Af(('(.)P&'#'")#?77)&()B'()6'7/#87'"(9%:#'()S(8'"#8,8F'()S(B)gS#:;;'(E:##S(C'(-)
d'"C7'&$%')?B'"):S$%)FS#U8F7&$%')6'7/#8,/'"9",ES(C#E":C'()C'('"&'"'(.
)
)
!"#$%&'('()&(*)+",(('"-)+.-)!/('"-)0.)123245)6'7/#87'"(9%:#'();&8)<=)>%:8/?8#)@)A:(()
B:#)C'7&(C'(D)E(;:);:C:F&()3GH2324.)6.)GGIGJ.)
%889#*HHKKK.E(;:.:8H$?(8'(8HB?K(7?:BHJGLMH23LJ4DN'"#&?(OJ
)
)
)
P'")=(E?";:8&AR&8)>%:8/?8)&#8):SE)h'B'")0QQ>)<S"##'&8')&(8'C"&'"8-):B:98&'"8)N?()+",(('")
i)!/('")1&()P"S$A5
)
)
Z'$%(&#$%)/:#&'"8)B'")>%:8/?8):SE)'&(';)j'8"&'N:7)WSC;'(8'B)V'('":8&?()1jWV5)6b#8';)
;&8)W(/&(BS(C):()'&()]:"C')]:(CS:C')0?B'7):SE)'S"?9U&#$%'()6'"N'"(.)Y:$%)B'")
!&(K&77&CS(C)&()B&')P:8'(N'":"/'&8S(C)'"#$%'&(8)B'")>%:8/?8):SE)h'B'")<S"##'&8'-)'&(')
K'&8'"')j'C&#8"&'"S(C)&#8)(&$%8)'"E?"B'"7&$%.)Y'/'()B'()"'$%87&$%'()R":C'#8'77S(C'()K:")
'#)'&(')k'":S#E?"B'"S(C-):77')=(%:78')B'#)0QQ>#)A?""'A8)&()B'")d'A8?"B:8'(/:(A)B'#)
>%:8/?8#):/FS/&7B'(.)
)
)
g&'7)B'#)>%:8/?8#)K:")'#-)B&')68SB&'"'(B'()/'&;)]'"('()FS)S(8'"#8,8F'(.)!&(')E"'&K&77&C')
:(?(b;')[;E":C')1Y)O)LM-)+'(S8F'"*&(('()()O)4M-)(&$%8)+'(S8F'"*&(('()()O)235)(:$%)B'")
]'%"N'":(#8:78S(C)%:8)'"C'/'(*)gS#:;;'(E:##S(C'(-)!"A7U"S(C'()S(B)`/S(C#E":C'()
#&(B)B&')%&7E"'&$%#8'()RS(A8&?('(.)P&')[;E":C')F'&C8'):/'"):S$%)'&('#)B'S87&$%*)P'")
>%:8/?8);?8&N&'"8')9'")#')(&$%8)FS;)]'"('()?B'")FS")d'"8&'ES(C.)6?K?%7)68SB&'"'(B'-)
B&')B'()>%:8/?8):A8&N)C'(S8F8)%:/'(-):7#):S$%)68SB&'"'(B'-)B&')B'()>%:8/?8)(&$%8):A8&N)
C'(S8F8)%:/'(-)K:"'()B&'#'")0'&(S(C.)P&'#')!"C'/(&##')K&B'"#9"'$%'()68SB&'(-)B&')
>%:8/?8#):7#)7'"(;?8&N&'"'(B)/'#$%"'&/'()1\?77(b)'8):7.-)232Gl)W&8)+:%:)'8):7.-)232J5-)
:S$%)]:/:BF')'8):7.)1232J5)K'&#'():SE)K&B'"#9",$%7&$%')+'ES(B')&()B'")]&8'":8S")%&(.
)
)
P&')WS#K'"8S(C)B'")+'E":CS(C'()'"C:/)'&()K'&8'"'#)&(8'"'##:(8'#)+&7B*)P&')
68SB&'"'(B'(-)B&')B'()>%:8/?8)(&$%8)C'(S8F8)%:/'(-)#$%U8F8'()B'()>%:8/?8):7#)
%&7E"'&$%'")'&():7#)B&'h'(&C'(-)B&')&%()8:8#U$%7&$%)C'(S8F8)%:/'(.)P&'#')`/'"#$%U8FS(C)
?B'"),/'"8"&'/'(')!"K:"8S(C)Af((8'();&8)B'")kb9'I+S//7'-)B&')B&'#')Z'$%(?7?C&')
S;C&/8-),/'"'&(#8&;;'()S(B)&;)/'A:((8'()Y'S&CA'&8#I!a'A8)/'C",(B'8)#'&(.
)
)
`/'")Mmn)B'")68SB&'"'(B'(-)#?K?%7)B'")YS8F'"*&(('():7#):S$%)B'")Y&$%8(S8F'"*&(('(-)
K,(#$%'()#&$%-)B:##)B'")>%:8/?8)&;)(U$%#8'()c:%")K&'B'"):(C'/?8'()K&"B.)+'F,C7&$%)
B'#)RS(A8&?(#S;E:(C#)B'#)>%:8/?8#)C:/),/'")'&()R,(E8'7)1()O)GJ5)B'")68SB&'"'(B'()&()
R"'&8'_8:(8K?"8'():(-)B:##)#&')#&$%)'&('()>%:8/?8);&8)C'(:S)B'()C7'&$%'()RS(A8&?('()
K,(#$%'(-)K&')#&')B'"F'&8)FS")d'"E,CS(C)#8'%'(.)c'K'&7#)'&()K'&8'"'#)R,(E8'7)(:((8')
!"A7U"S(C'()1()O)GJ5)/FK.)B:#)!"#8'77'()N?()R":C'()1()O)G25):7#)F'(8":7')RS(A8&?(.)
)
)
!#)F'&C8)#&$%-)B:##)68SB&'"'(B')=(8'"'##'):()>%:8/?8#)%:/'(.)!&(')FSA,(E8&C')=(8'C":8&?()
N?()E:$%#9'F&o#$%';)X"?;98)!(C&(''"&(C):7#)]'"(&(%:78)&()B'()+",$A'(AS"#)KU"')
,/'"7'C'(#K'"8.)W(C'#&$%8#)B'")%?%'()gS#8&;;S(C)FS")\'&8'"E,%"S(C)B'#)>%:8/?8#)
!"#$%&'('()&(*)+",(('"-)+.-)!/('"-)0.)123245)6'7/#87'"(9%:#'();&8)<=)>%:8/?8#)@)A:(()
B:#)C'7&(C'(D)E(;:);:C:F&()3GH2324.)6.)GGIGJ.)
%889#*HHKKK.E(;:.:8H$?(8'(8HB?K(7?:BHJGLMH23LJ4DN'"#&?(OJ
)
)
#8'778)#&$%)FSB';)B&')R":C'-)?/)S(B)K&')'&(')=(8'C":8&?()&()K'&8'"')]'%"N'":(#8:78S(C'()
#&((N?77);fC7&$%)KU"'.)=()]'%"N'":(#8:78S(C'(-)&()B'('()B:#)6'7/#8#8SB&S;)'&('()%?%'()
W(8'&7)%:8-)&#8)'&(')=(8'C":8&?()'&('#)>%:8/?8#)BS"$%:S#)'&(')#&((N?77')!"CU(FS(C.)
)
)
P&')9?#&8&N'()!"E:%"S(C'():S#)B&'#';)X&7?8I!&(#:8F)F'&C'(-)B:##)<=IC'#8,8F8')
]'"(S(8'"#8,8FS(C)'&()K'"8N?77'#)Z??7)FS")&(B&N&BS:7&#&'"8'()Rf"B'"S(C)#'&()A:(()I)
N?":S#C'#'8F8-)#&')K&"B)C'F&'78)&()B&B:A8&#$%')<?(F'98')'&(C'/S(B'()S(B)'(8#9"'$%'(B)
eS:7&8:8&N)'(8K&$A'78.
)
)
)
W&8)+:%:-)Z.-)!7)k:hh&-)0.-)!#I6::Bb-)p.-)i)R:B&7&-)k.)1232J5.)Z%')&;9:$8)?E)'BS$:8&?(:7)
$%:8/?8)?()#8SB'(8)7':"(&(C)'_9'"&'($'.)=()!BS$:8&?():(B)=(E?";:8&?()Z'$%(?7?C&'#)
1+B.)2M-)=##S')m-)6.)G3G4J@G3GLq5.)69"&(C'")6$&'($'):(B)+S#&('##)0'B&:)]]>.)
%889#*HHB?&.?"CHG3.G33LH#G3qJMI32JIG2GqqIK)
)
+",(('"-)+.)i)!/('"-)0.)1&()P"S$A5.)=(E?R&8):(B)+'b?(B*)W=)>%:8/?8#):#)!BZ'$%)Z??7#)E?")
6'7EIj'CS7:8'B)]':"(&(C)&()0QQ>#.)W$$'98'B)E?")2L8%)=(8'"(:8&?(:7)>?(E'"'($')?()
kS;:(I>?;9S8'")=(8'":$8&?(.)]'$8S"')Y?8'#)&()>?;9S8'")6$&'($'.)69"&(C'"-)>%:;.
)
+",(('"-)+.-)R&(B'(&C-)<.)i)!/('"-)0.)1232^5.)P&C&8:7)]':"(&(C)BS"&(C)>Qd=PIGM.)W)
6b#8';:8&$)j'N&'K):(B)0'8:IW(:7b#&#)?E)P&#8:($')]':"(&(C):8)[(&N'"#&8&'#)&()WS#8"&:)
=()Z.)+:#8&:'(#)1!B.5-)X"?$''B&(C#)?E)!B0'B&:)r)=((?N:8')]':"(&(C)199.)Mm3IMmm5.)
+"S##'7#-)+'7C&S;*)W##?$&:8&?()E?")8%')WBN:($';'(8)?E)>?;9S8&(C)&()!BS$:8&?()
1WW>!5.)%889#*HH7':"(8'$%7&/.?"CH9"&;:"bH9H22^qGLH
)
]:/:BF'-)].-)V"&C?7&:-)0.-)i)0:$%:&BF'-)].)1232J5.)j?7')?E)W=)$%:8/?8#)&()'BS$:8&?(*)
#b#8';:8&$)7&8'":8S"')"'N&'K.)=()=(8'"(:8&?(:7)c?S"(:7)?E)!BS$:8&?(:7)Z'$%(?7?Cb)&()
k&C%'")!BS$:8&?()1+B.)23-)=##S')G5.)69"&(C'")6$&'($'):(B)+S#&('##)0'B&:)]]>.)
%889#*HHB?&.?"CHG3.GGmqH#^G2JMI32JI33^2qIG
)
Z[)V":F)]'%"I)S(B)]'"(8'$%(?7?C&'(.)1232^5.)0QQ>#)i)]'%"'*)W$%8)]'%"I)S(B)
]'"(#F'(:"&'();&8)0QQ>#.)V":F)[(&N'"#&8b)?E)Z'$%(?7?Cb.)
%889#*HHB?&.?"CHG3.J2GLH<jcjJI3kkMJ
)
\?77(b-)6.-)6$%('&B'"-)c.-)P&)0&8"&-)P.-)\'&B7&$%-)c.-)j&88/'"C'"-)0.-)i)P":$%#7'"-)k.)1232G5.)
W"')\')Z%'"')p'8D)I)W)6b#8';:8&$)]&8'":8S"')j'N&'K)?()>%:8/?8#)&()!BS$:8&?(.)=()
R"?(8&'"#)&()W"8&o$&:7)=(8'77&C'($')1+B.)^5.)R"?(8&'"#)0'B&:)6W.)
%889#*HHB?&.?"CHG3.JJmMHE":&.232G.q4^M2^
)
ResearchGate has not been able to resolve any citations for this publication.
Digital Learning during COVID-19. A Systematic Review and Meta-Analysis of Distance Learning at Universities in Austria
Conference Paper
Full-text available
  • Jul 2024
The COVID-19 pandemic has greatly affected universities in Austria, leading to a rapid shift to distance learning. This study analyzed 59 surveys conducted between March 2020 and October 2021. The quality of distance learning varies among universities and lecturers. Effective communication and access to information along with an appropriate workload for online teaching are key aspects. Adequate examination dates, seats, and time to complete courses are necessary. Students appreciated video recordings and some examination formats but preferred face-to-face exams in the future. This shows that online teaching is useful as a complement but not in itself. Using blended and hybrid learning methods can preserve the identified advantages.
View
Role of AI chatbots in education: systematic literature review
Article
Full-text available
  • Oct 2023
AI chatbots shook the world not long ago with their potential to revolutionize education systems in a myriad of ways. AI chatbots can provide immediate support by answering questions, offering explanations, and providing additional resources. Chatbots can also act as virtual teaching assistants, supporting educators through various means. In this paper, we try to understand the full benefits of AI chatbots in education, their opportunities, challenges, potential limitations, concerns, and prospects of using AI chatbots in educational settings. We conducted an extensive search across various academic databases, and after applying specific predefined criteria, we selected a final set of 67 relevant studies for review. The research findings emphasize the numerous benefits of integrating AI chatbots in education, as seen from both students' and educators' perspectives. We found that students primarily gain from AI-powered chatbots in three key areas: homework and study assistance, a personalized learning experience, and the development of various skills. For educators, the main advantages are the time-saving assistance and improved pedagogy. However, our research also emphasizes significant challenges and critical factors that educators need to handle diligently. These include concerns related to AI applications such as reliability, accuracy, and ethical considerations.
View
The impact of educational chatbot on student learning experience
Article
Full-text available
  • Sep 2023
  • Educ Inform Tech
Artificial Intelligence (AI) technologies have increasingly become vital in our everyday lives. Education is one of the most visible domains in which these technologies are being used. Conversational Agents (CAs) are among the most prominent AI systems for assisting teaching and learning processes. Their integration into an e-learning system can provide replies suited to each learner's specific needs, allowing them to study at their own pace. In this paper, based on recent advancements in Natural Language Processing (NLP) and deep learning techniques, we present an experimental implementation of an educational chatbot intended to instruct secondary school learners Logo, an educational programming language. The related chatbot was implemented and evaluated in Moroccan public schools with the support of teachers from the Regional Center for Education and Training Professions of Souss Massa. The experiments included 109 students grouped into three separate classes. One is a control class group that uses a traditional approach, while the other two are experimental groups that employ digital content and the chatbot-based method. Preliminary findings indicate that employing chatbots can greatly enhance student learning experiences by allowing them to study at their own speed with less stress, saving them time, and keeping them motivated. Furthermore, integrating these AI systems into a smart classroom will not only create a supportive environment by encouraging good interactions with students, it will also allow learners to be more engaged and achieve better academic objectives.
View
Are We There Yet? - A Systematic Literature Review on Chatbots in Education
Article
Full-text available
  • Jul 2021
Chatbots are a promising technology with the potential to enhance workplaces and everyday life. In terms of scalability and accessibility, they also offer unique possibilities as communication and information tools for digital learning. In this paper, we present a systematic literature review investigating the areas of education where chatbots have already been applied, explore the pedagogical roles of chatbots, the use of chatbots for mentoring purposes, and their potential to personalize education. We conducted a preliminary analysis of 2,678 publications to perform this literature review, which allowed us to identify 74 relevant publications for chatbots’ application in education. Through this, we address five research questions that, together, allow us to explore the current state-of-the-art of this educational technology. We conclude our systematic review by pointing to three main research challenges: 1) Aligning chatbot evaluations with implementation objectives, 2) Exploring the potential of chatbots for mentoring students, and 3) Exploring and leveraging adaptation capabilities of chatbots. For all three challenges, we discuss opportunities for future research.
View
Association for the Advancement of Computing in Education
  • Belgium Brussels
Brussels, Belgium: Association for the Advancement of Computing in Education (AACE). https://learntechlib.org/primary/p/224617/
  • Jan 2024
  • Tu Graz Lehr-Und Lerntechnologien
TU Graz Lehr-und Lerntechnologien. (2024). MOOCs & Lehre: Acht Lehr-und Lernszenarien mit MOOCs. Graz University of Technology. https://doi.org/10.3217/KRJR3-0HH93