Challenges and Opportunities in Integrating Interactive Chatbots into Code Review Exercises: A Pilot Case Study

Juan Carlos Farah, Denis Gillet, Adrian Christian Holzer
IATED, 2022
Article de conférence

Résumé

While chatbots are commonly used to support software developers with repetitive tasks, their use in programming education is still limited, particularly for students in non-technical domains. To better understand the potential for chatbots to support programming education, we conducted a pilot case study aimed at integrating interactive chatbots into an online lesson on programming best practices. Using an educational application simulating the code review process, students were introduced to Python code style guidelines as a part of their practical work for a course on computational thinking aimed at non-technical graduate students. Our mixed-method analysis sheds light on the opportunities and challenges affecting the implementation of our chatbot integration and its potential for adoption in programming education. While we identified opportunities to guide students through predefined conversational pathways, provide students with personalized content, allow students to request support from the instructor, and incorporate humor into the learning process, we also encountered challenges involving configuration, repeated exposures, and limited scripts. These findings have implications that affect the design considerations of the technological and pedagogical aspects of our chatbot integration, which are relevant to educators and researchers in digital education looking to incorporate similar chatbot technologies into their practice. Strategies for harnessing these opportunities and addressing these challenges in future work are discussed.

Official source

https://infoscience.epfl.ch/record/294069?ln=fr

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Concepts associés

Chargement

Publications associées

Chargement

Juan Carlos Farah, Denis Gillet, Adrian Christian Holzer
IATED, 2022
Article de conférence

Résumé

Official source

https://infoscience.epfl.ch/record/294069?ln=fr

À propos de ce résultat

Concepts associés (14)

Concepts associés

Chargement

Publications associées (2)

Publications associées

Chargement

, , , ,

Over the past decade, the use of chatbots for educational purposes has gained considerable traction. A similar trend has been observed in social coding platforms, where automated agents support software developers with tasks such as performing code reviews. While incorporating code reviews and social coding platforms into software engineering education has been found to be beneficial, challenges such as steep learning curves and privacy considerations are barriers to their adoption. Furthermore, no study has addressed the role chatbots play in supporting code reviews as a pedagogical tool. To help address this gap, we developed an online learning application that simulates the code review features available on social coding platforms and allows instructors to interact with students using chatbot identities. We then embedded this application within a lesson on software engineering best practices and conducted a controlled in-class experiment. This experiment examined the effect that explaining content via chatbot identities had on three aspects: (i) students’ perceived usability of the lesson, (ii) their engagement with the code review process, and (iii) their learning gains. While our findings show that it is feasible to simulate the code review process within an online learning platform and achieve good usability, our quantitative analysis did not yield significant differences across treatment conditions for any of the aspects considered. Nevertheless, our qualitative results suggest that students expect explicit feedback when performing this type of exercise and could thus benefit from automated replies provided by an interactive chatbot. We propose to build on our current findings to further explore this line of research in future work.

IEEE2022

Chargement

Science, Technology, Engineering and Mathematics (STEM) education is recognized as a top priority for school education worldwide and Inquiry-based teaching and learning is identified as one of the most dominant approaches. To effectively engage individual students in Inquiry tasks, appropriate guidance needs to be provided, usually by combining different digital tools such online labs, data analysis tools and modelling tools. This is a cumbersome task for teachers to perform manually since it involves (a) assessing during the education design, the type and level of tool-supported guidance to be provided to students and (b) potentially refining this level and types to meet the guidance needs of individual students based on educational data from the delivery of the educational design. Thus, in our research we target to investigate how to support this process with educational data analytics methods and tools from both the design and the delivery of educational designs, that inform teachers’ decision making for systematic reflection. To this end, the contribution of this paper is the design and evaluation of a novel “Teaching and Learning” Analytics method and supporting research prototype tool, extending the scope of purely learning analytics methods, to (a) analyze inquiry-based educational designs in terms of the tool-supported guidance they offer and (b) relate these analyses to students' educational data that are already being collected by existing learning analytics systems, so as to increase teachers’ awareness and understanding and scaffold their reflection. A two-layer evaluation methodology was adopted to evaluate both the capacity of our method to analyze educational designs in terms of appropriate guidance as well as to investigate whether the insights generated by the method offer statistically significant indicators that impact students' activity during the delivery of these educational designs. The results obtained, based on real-life educational data, argue that the proposed method and tool can support teachers to accurately analyse Inquiry-based educational designs and receive meaningful insights to improve and tailor students' learning experiences. The insights of this work aim to contribute in the research field of cognitive data analytics for teaching and learning, by investigating new ways to combine analyses of the educational design and the students’ activity, so as to inform teachers’ reflective decision making from a holistic perspective

2019

Chargement

2019