Autonomous learning has an important role in online learning because teachers cannot directly supervise the student learning process, which makes students themselves responsible for their learning. As an attempt to provide teachers with an alternative autonomous learning medium, this study aimed to use a chatbot-based Japanese grammar learning application namely Gengobot as an autonomous Japanese learning medium. This study applied Analysis, Design, Development, Implementation, and Evaluation (ADDIE) instructional design model. The data of this research was collected using a pre-experimental method and distributed a Likert scale questionnaire to 50 Japanese language learners with Japanese language levels equivalent to or less than JLPT level N3. The results showed that Gengobot as a chatbot-based Japanese grammar learning medium is an interesting and innovative medium to support Japanese autonomous learning because learners can decide how they learn using this application to improve their Japanese grammar skills. In addition, Gengobot is a chatbot-based learning medium that is more interactive than other Mobile-based media, which makes learners more interested in using Gengobot as a Japanese grammar learning medium. However, Gengobot still needs further development such as adding advanced grammar content (N2 and N1), adding Japanese pronunciation features (audio), etc.

This study aims to compare students’ Japanese language grammar ability, between students who practice with a chatbot-based application (Gengobot) with students who do not use the application. This research was conducted using quantitative experimental research methods, with experimental class and control class. The subjects of this research were 22 Japanese language students. The results showed that the grammar ability of students who used Gengobot application as a training medium improved significantly than students who used conventional media as paper works. Factors that cause these differences are the use of cognitive and behavioristic approaches in applications, as well as the use of media, which is more practical and engaging. The questionnaire regarding student responses to the Gengobot application shows positive results. Things that need to be considered in future research are the development of the Gengobot application to be more flexible and to add more material to the application.

This study sought to examine vocational students’ evaluation and feedback regarding the chatbot-based application as an assistive technology in learning basic Japanese in vocational high school and investigate students’ recommendations on the possible future advancement of the chatbot-based application to help students learn the Japanese language better. This study employed a questionnaire and follow-up interview to collect the data, which questionnaire was administered to 100 vocational students enrolled in 8 state vocational high schools located in different regions in Indonesia. The data collected were analysed using SPSS 24, and also tested for reliability and validity. The findings of this study denote the use of the chatbot-based application, namely Gengobot, useful in enhancing students’ basic Japanese grammar learning, improving vocabulary mastery related to vocational terminologies, providing practices for basic Japanese language level exercise, having attractive and interactive features, and fostering learners’ autonomy and independence learning due to its practicality, portability, accessibility, and flexibility. The results also conveyed the practicality problems and confusion in using the application as an application integrated into social media. Hence, further development of the chatbot-based application Gengobot as assistive technology in learning Japanese is recommended. All in all, the chatbot-based application Gengobot as an assistive Japanese language learning application can be concluded as compelling, and is recommended to be used for vocational students to enhance autonomous learning as well as to support distance learning.