EASEAI 2019- Proceedings of the 1st ACM SIGSOFT International Workshop on Education through Advanced Software Engineering and Artificial Intelligence

Full Citation in the ACM Digital Library

SESSION: Programming Education and Digital Literacy Awareness

Engaging children in the smart city: a participatory design workshop

Nowadays, smart city is a term recurring in many political discourses and in literature. Indeed, smart cities provide innovative solutions to solve urban issues. However, this concept and its implications remain obscure to the larger public. In order to help younger citizens understand what lies behind the smart city, we developed a workshop aiming at introducing the concept of smart city in all its complexity. We present here the results of the first in-school session of the workshop. It shows promising results on the engagement of children as well as an evolution in their understanding of the smart city.

Designing personalized learning environments through monitoring and guiding user interactions with code and natural language

Learning the vocabulary of a new language and a new programming API are similar in multiple ways. In this paper we evaluate several of the similarities and show that based on them we can design systems that can guide the learner towards improving their knowledge without an external tutor or preset curriculum. Instead, the class of systems we propose here are based on automated approaches of building maps of knowledge of the domain by mining repositories. By intersecting this knowledge with models of learner knowledge built by observing past learner interactions with artifacts of the domain we can generate highly personalized learning guidance.

Analysis of students’ preconceptions of concurrency

In previous literature, several authors have recommended teaching concurrent programming, as the current evolution of IT involves concurrency. However, in order to teach concurrent programming properly, in a constructivist educational learning framework, we need to know the preconceptions students have regarding it. In this paper, we report on the results found from data collected through a questionnaire submitted in secondary schools to 101 students aged from 12 to 15. We detail the preconceptions of concurrent programming we extracted from the questionnaire answers and formulate recommendations toward creating a course teaching concurrent programming.

SESSION: Automated Feedback and Evaluation Systems

Open knowledge interface: a digital assistant to support students in writing academic assignments

In the course of their studies, the majority of students at German universities have to write a certain number of academic assignments as an essential part of the academic training in any degree program. This work presents some initial results of our research into the design, implementation and conceptual usage of OKI (Open Knowledge Interface) – a digital assistant intended to support students in writing academic assignments. The core aspects of assistance include project management, context-sensitive help in applying scientific methods and search in open access literature. OKI is a conversational chatbot running inside Telegram-Messenger and allowing an efficient mobile usage, and thus a flexible way of organizing users’ own time and workload. The Open Knowledge Interface project is funded by the German Federal Ministry of Education and Research within the Open Access Guideline, and runs from May 2018 to October 2019. This paper therefore is an attempt to describe some initial conceptual thoughts as well as preliminary results including first user experiences and a brief outlook on future work.

Towards context-aware automated writing evaluation systems

Writing is a crucial skill in our society, which is regularly exerted by students across all disciplines. Automated essay scoring and automatic writing evaluation systems can support professors in the evaluation of written texts and, conversely, help students improving their writing. However, most of those systems fail to consider the context of the writing, such as the targeted audience and the genre. In this paper, we depict our vision towards new-generation AES systems that could evaluate written products while considering their specific context. In education, such tools could support students not only in adapting their written product to their particular context, but also in identifying points for improvement and situational settings where their writing is less proficient.

Application of data clustering for automated feedback generation about student well-being

Investment in the well-being of today’s schoolchildren is an important investment in the future. We believe that learning does not happen in the absence of well-being. This data-oriented research studies how automation utilizing data analysis algorithms could help provide the students with feedback and guidance about their well-being related issues. We implemented a system that combines data processing methods and research-based knowledge to serve that purpose.

Our target was to develop an automated feedback system utilizing information from a large data set collected from well-being surveys from students, as well as research-based well-being knowledge. The system can be used to provide automated feedback for students who answer a well-being survey.

SESSION: Teaching Advanced Software Engineering

Does learning by doing have a positive impact on teaching model checking?

The theory of education Learning by doing exposed by Dewey theorized that learning should be relevant and practical, not just passive and theoretical.

The aim of this study is twofold: firstly to report on the effort related to the improvement of usability of a model checker tool by master students enrolled in the Software Engineering and Distributed Systems in Internet sections in our university, and secondly to investigate if the integration of research-based assignment into teaching and learning favorably influence learning.

The results of quantitative analysis (perceptions and opinions of the students collected through surveys and an independent t-test statistical test) acknowledge the effectiveness and efficiency of learning by doing approach in teaching model checking, both concepts and tool’s usability.

The results of qualitative analysis (discussions, perceptions and opinions of both students and teacher) recognize the importance of learning by doing activities (poster creating and presenting, project-based assignment, research based assignment) in teaching/learning model checking.

Artificial intelligence meets software engineering in the classroom

We aimed to assess the reliability of teaching Artificial Intelligencefor Software Engineering master students. We propose a semi-interactive course where the students have to develop applications for solving real world problems by using various intelligent tools. We try to integrate these two disciplines, since both deal with modeling of the real case studies, sharing some common elements.We report on a study that we conducted on observing student teams as they develop AI-based applications. We validate the proposed semi-interactive course by using various criteria. In addition, we checked if some best practices from industrial teams are followed by our students.

Advances in designing a student-centered learning process using cutting-edge methods, tools, and artificial intelligence: an e-learning platform

It is well known the fact that learning process is difficult for learners and at the same time it raises problems for those who teach. Teaching Software Engineering for undergraduate students is an assiduous and a challenging task due to its level of abstraction, to frequently changes that appear in programming paradigms and in software development methodologies.

In this paper we provide a novel approach in teaching Advanced Programming Methods, the third introductory course in Software Engineering that is being taught at our faculty within the Computer Science Curriculum for undergraduate students.

The contribution of this paper is threefold: firstly, we design a student-centered learning process intertwining cutting edge methods like for instance project-based learning, self assessment-based learning and students engagement. Secondly, we design an E-learning platform to provide for students an automated assessment and appropriate feedback and, most important, to offer them support throughout the learning process. Thirdly, we provide a quantitative and qualitative analysis over 3 years of teaching Advanced Programming Methods course, by applying the proposed methodology.

Our analysis results show the effectiveness of our approach. Key contributions in this paper are our proposed E-learning platform and the analysis findings.