Developing Bosnian/Croatian/Serbian Conversational Chatbots Using MYAI Builder

The present paper reports on the development of Bosnian/Croatian/Serbian Novice and Intermediate Chatbots at Arizona State University. The principal AI platform used for this course is MyAI Builder, an open AI development tool. In the initial phase of this project, from the summer of 2000 to the Fall of 2022, materials to be used as the input for the platform were gathered. Various lexical lists and other materials were gathered along with developing an interactive platform. Next, numerous materials were selected by student researchers supported by ASU Melikian Center Research Grants. This is of particular importance given that it is likely to increase the interest of their fellow students in them. The two chatbots were created in the fall of 2024 and their testing has started. The paper reports on the first, overwhelmingly positive, round of feedback from students, which, at this point, is just the first indication of the chatbots’ performance. There are several takeaways from this project. First, it is important to emphasize the benefits of using open AI platforms that enable control of the knowledge base and thus limit the number of hallucinations. Second, it is important to involve students in developing this educational platform so that the content is appealing to prospective users. Third, it is important to integrate existing pedagogical and reference materials into this platform. Finally, finding the most suitable large language model is of the utmost importance.

Authors

Publication Details

Journal
Russian Language Journal
Published
2024-12-30
DOI
https://doi.org/10.70163/0036-0252.1402
Primary Topic
AI in Service Interactions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Developing Bosnian/Croatian/Serbian Conversational Chatbots Using MYAI Builder

Danko Šipka
Russian Language Journal
AI in Service Interactions
article

Developing Bosnian/Croatian/Serbian Conversational Chatbots Using MYAI Builder

Danko Šipka
article en

Abstract

The present paper reports on the development of Bosnian/Croatian/Serbian Novice and Intermediate Chatbots at Arizona State University. The principal AI platform used for this course is MyAI Builder, an open AI development tool. In the initial phase of this project, from the summer of 2000 to the Fall of 2022, materials to be used as the input for the platform were gathered. Various lexical lists and other materials were gathered along with developing an interactive platform. Next, numerous materials were selected by student researchers supported by ASU Melikian Center Research Grants. This is of particular importance given that it is likely to increase the interest of their fellow students in them. The two chatbots were created in the fall of 2024 and their testing has started. The paper reports on the first, overwhelmingly positive, round of feedback from students, which, at this point, is just the first indication of the chatbots’ performance. There are several takeaways from this project. First, it is important to emphasize the benefits of using open AI platforms that enable control of the knowledge base and thus limit the number of hallucinations. Second, it is important to involve students in developing this educational platform so that the content is appealing to prospective users. Third, it is important to integrate existing pedagogical and reference materials into this platform. Finally, finding the most suitable large language model is of the utmost importance.

Russian Language JournalVol. 74(1)
Openalex Percentile: Top 75%
AI in Service Interactions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.