Competitive programming in computational thinking and problem solving education

Building practical programming competency requires a long-lasting journey of discovery, trial and error, learning and improvement. This article presents essential findings of a case study of a Python programming contest with an automatic judgement system for Competitive Programming training extending the learning experiences for students in an introductory course, computational thinking and problem-solving. The benefits and challenges are discussed. Due to the coronavirus disease 2019 (COVID-19) epidemic, a hybrid model of the contest was adopted, that is, some students participated in the contest on-site, while others participated remotely. To alleviate human effort in judging the submissions, the DOMjudge platform, a web-based automatic judgement system, has been deployed as an online automatic judgement system and contest management in competitive programming. The implementation roadmap and framework were provided. The contest problems and contestants' performances were discussed. Not many junior contestants could solve at least one problem(s), and competitive computing training should be offered if the students are keen on open competitions. An empirical study was conducted to evaluate the student feedback after the contest. Preliminary results revealed that the contest offering the chance to stimulate student learning interests could enhance their independent learning, innovative thinking and problem-solving skills, and could thus lead to the overall benefits of the learning experiences, which further encourage them to participate in future contests to improve their learning and therefore enhance their employability. Employers often treasure student experiences in competitive programming events, like association for computing machinery programming contests, Google Code Jam or Microsoft Imagine Cup. Sharp vision requiring skills to tackle unseen problems within a short period is also instrumental to students planning for graduate school. © 2023 Wiley Periodicals LLC.

Suicide Ideation Detection on Social Media During COVID-19 via Adversarial and Multi-task Learning

Suicide ideation detection on social media is a challenging problem due to its implicitness. In this paper, we present an approach to detect suicide ideation on social media based on a BERT-LSTM model with Adversarial and Multi-task learning (BLAM). More specifically, BLAM combines BERT model with Bi-LSTM model to extract deeper and richer features. Furthermore, emotion classification is utilized as an auxiliary task to perform multi-task learning, which enriches the extracted features with emotion information that enhances the identification of suicide. In addition, BLAM generates adversarial noise by adversarial learning improving the generalization ability of the model. Extensive experiments conducted on our collected Suicide Ideation Detection (SID) dataset demonstrate the competitive superiority of BLAM compared with the state-of-the-art methods. © 2021, Springer Nature Switzerland AG.