{"title":"Designing an Educational Chatbot with Joint Intent Classification and Slot Filling","authors":"Yujia Wang, Shuqi Liu, Linqi Song","doi":"10.1109/TALE54877.2022.00069","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00069","url":null,"abstract":"In the post-pandemic era, with the continuous shifting trend from offline to online teaching mode and the development of technologies in virtual communication, the necessity of a virtual assistant for education-related application scenarios is gradually being recognized. However, simple and educational domain-specific chatbot is not well studied. In this work, we develop an educational chatbot based on a Natural Language Understanding (NLU) model that can understand task-oriented natural language texts to provide education-related services. The NLU model utilizes a large pre-trained language model of BERT variants as backbones to jointly optimize intent classification and slot filling modules, enabling the proposed educational opendomain goal-oriented intrapersonal chatbot to capture critical information from user queries. Our system achieves good performance. The system is demonstrated to be able to assist in reducing the communication burden between students and teachers in the online teaching environment, ease the shift of students from physical to virtual classrooms, and alleviate the pressure on the teaching staff.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122833045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sakib Ullah Sourav, Violetta Chunyu Hou, Sophia Linda Morsten, Cristina Diordieva, Jeffrey Radloff, Mihwa Park, Ibrahim H. Yeter
{"title":"Exploring Engineering Education in Bangladesh, Hong Kong, Singapore, and Switzerland: An International Perspective","authors":"Sakib Ullah Sourav, Violetta Chunyu Hou, Sophia Linda Morsten, Cristina Diordieva, Jeffrey Radloff, Mihwa Park, Ibrahim H. Yeter","doi":"10.1109/TALE54877.2022.00132","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00132","url":null,"abstract":"This conceptual article examines engineering education practices across Bangladesh, Hong Kong, Singapore, and Switzerland towards contributing to an international definition of \"global engineering.\" While the overarching goal of engineering is the collective improvement of industry and development, engineering can look very different globally, especially in engineering education. Through profiling engineering education internationally, we seek to emphasize similarities and differences in its application towards synthesizing a set of shared practices and considerations.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127015243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Managing Motivation and Information Processing of Students in a Learning Analytics Course during Emergency Remote Teaching","authors":"Chi-Un Lei","doi":"10.1109/TALE54877.2022.00086","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00086","url":null,"abstract":"Various educational initiatives and curricula have been proposed to cultivate more learning analytics talents. However, only scattered studies have shown how learning analytics has been taught more effectively. Meanwhile, there are limited studies on analysing students’ motivation, volition and information processing during emergency remote teaching. In the Spring 2022 semester, the author taught a learning analytics course in an ERT situation without any notice in advance. After the semester, the author conducted a retrospective analysis to identify what instructional strategies had been unintentionally adopted, based on an integrated model of motivation, volition and performance proposed by Keller. This manuscript is on the analysis of how instructional strategies had been deployed. Recommended strategies have been proposed for adoption in the future.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116531424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Identification, Relevance, and Limitations of Threshold Concepts in Electrical and Electronic Engineering","authors":"Zohaib Akhtar","doi":"10.1109/TALE54877.2022.00037","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00037","url":null,"abstract":"This paper discusses the identification, relevance, and limitations of threshold concepts in electrical and electronic engineering (EEE). Initially, a brief introduction to threshold concepts is provided for readers unfamiliar with the topic. After that, key threshold concepts in EEE are identified, and conclusions are drawn about their usefulness in teaching. Finally, the limitations of threshold concepts are discussed. The paper focuses on the first two years of the EEE degree, as the first two years are the core years where all students study compulsory modules. In the last two years, the threshold concepts can depend upon the chosen area of specialisation. It is concluded that despite all the limitations, identifying the threshold concepts can be a valuable exercise for the teachers who design the modules.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"485 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127568659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Smart Driving Gesture Interaction Design Based On DMPT Compatibility Model","authors":"Fenghong Wang, Yuheng Pang, Zhongyi Yang","doi":"10.1109/TALE54877.2022.00092","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00092","url":null,"abstract":"To address the problem of generally poor user experience of existing automotive gesture interaction products, the intelligent driving gesture interaction system is designed and the problem point design experiments are verified and optimized. The study combines the human-computer interaction compatibility theory in engineering psychology and constructs a DMPT compatibility model to guide the subsequent Situational Analysis and gesture interaction system design process. Experiments are designed and optimized for the problem of the impact of abstracted legends on driver cognitive load presented in the evaluation, which is a reference for the development of smart driving gesture interaction.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133253006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiang Zhang, Bruce X. B. Yu, Yan Liu, Gong Chen, G. Ng, N. Chia, E. H. So, S. So, V. Cheung
{"title":"Conversational System for Clinical Communication Training Supporting User-defined Tasks","authors":"Xiang Zhang, Bruce X. B. Yu, Yan Liu, Gong Chen, G. Ng, N. Chia, E. H. So, S. So, V. Cheung","doi":"10.1109/tale54877.2022.00071","DOIUrl":"https://doi.org/10.1109/tale54877.2022.00071","url":null,"abstract":"Effective clinical communication is essential for delivering safe and high-quality patient care, especially in emergent cases. Standard communication protocols have been developed to improve communication accuracy and efficiency. However, traditional training and evaluation require substantial manpower and time, which can be infeasible during public crises when training is most needed. This research aims to facilitate autonomous, low-cost, adaptive clinical communication training via artificial intelligence (AI)-powered techniques. We propose a conversational system for clinical communication training supporting user-defined tasks. Two data augmentation (DA) methods, term replacement and context expansion, are proposed to allow non-professional users to create Al models with a small number of samples. Equipped with biomedical ontology and pre-trained language models, our system is able to simulate clinical communication scenarios, provide timely evaluation, and adapt to new tasks with minimal editing. Various experiments demonstrate that our proposed algorithms can achieve satisfactory performance using a small amount of training data. Real-world practice in local hospitals shows that our system can provide expert-level evaluation and deliver effective clinical communication training.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134404495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Purnima Murali Mohan, Vivek Balachandran, Ong Ze Quan, Jas Pang Ze Xin, D. Divakaran
{"title":"NFT-Merit: An NFT-based Module Credit Management System on Ethereum Blockchain","authors":"Purnima Murali Mohan, Vivek Balachandran, Ong Ze Quan, Jas Pang Ze Xin, D. Divakaran","doi":"10.1109/TALE54877.2022.00083","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00083","url":null,"abstract":"Blockchain is one of the most promising technology trends that has the potential to be extensively adopted in the education sector. In this work, we investigate the feasibility of utilizing an Ethereum blockchain for developing a trusted frame-work using ERC-721 non-fungible tokens (NFTs) for a Module credit management system – NFT-Merit. In this framework, the NFTs minted by a university represents the module credits issued by its faculty and owned by its students upon satisfying module requirements in the credit management system. Once a student has collected all the NFTs required for graduating the degree, a smart contract automatically generates a degree certificate which can be integrated with the well-known OpenCert formats. With cases of degree fraud on the rise, the current methods of degree issuance and verification are inadequate in this digital age. This research involves the design and development of a web-based decentralized application (dApp) on the Ethereum blockchain test network. The NFT-merit dApp is hosted on the InterPlanetary File System (IPFS) as a decentralized network of nodes instead of a single centralized node to enable redundancy, improve scalability and minimize network bandwidth usage for data access. We perform an extensive analysis of the costs involved in deploying NFT-merit and the duration of minting NFTs. Our experimental results show that minting NFTs in batches would require almost the same time as minting a single NFT in a transaction, whereas the cost savings in the former scenario is more than 22% as compared to the latter.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134409684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Scratch Project Analysis: Relationship Between Gender and Computational Thinking Skill","authors":"Rose Niousha, D. Saito, H. Washizaki, Y. Fukazawa","doi":"10.1109/TALE54877.2022.00099","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00099","url":null,"abstract":"The computer science industry suffers from a significant gender gap. This situation likely hinders the creation of inclusive and user-friendly systems due to a bias in perspectives. To narrow this gender gap, this study investigates how females program to increase interest in computer sciences. Specifically, 60 open Scratch projects on the web are analyzed to clarify differences in the Computational Thinking scores with respect to gender. The difference in the Computational Thinking score by gender suggests that the gap may be due to the lack of the Synchronization element in female users’ projects. A deeper understanding of how people program based on gender should support creating an effective and inclusive learning environment and allow educators to create programming materials that attract both genders equally into the field.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114423375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sukrit Leelaluk, T. Minematsu, Yuta Taniguchi, Fumiya Okubo, Takayoshi Yamashita, Atsushi Shimada
{"title":"Scaled-Dot Product Attention for Early Detection of At-risk Students","authors":"Sukrit Leelaluk, T. Minematsu, Yuta Taniguchi, Fumiya Okubo, Takayoshi Yamashita, Atsushi Shimada","doi":"10.1109/TALE54877.2022.00059","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00059","url":null,"abstract":"Students’ performance prediction is essential for instructors to observe each student’s learning behavior to discover which students have become at-risk. Early prediction helps instructors to intervene in time and provide academic support to these students. However, instructors should grasp essential behavior points to survey students’ academic performance. In this study, we propose the Scaled-Dot Product Attention that can mine the relationship between the student’s learning behaviors and performance to find the essential features that directly affect students’ performance. In this study, we tested the early prediction performance of Scaled-Dot Product Attention with conventional algorithms. We then investigated essential lectures or features related to students’ learning activities. From the result, we found that Scaled-Dot Product Attention outperformed the conventional algorithms to identify at-risk students and found the important lectures and students’ actions.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113967185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Student-Oriented Reform of Microelectronics Courses under the Background of Emerging Engineering","authors":"M. Tong, Jing Wen Hu, G. Wan","doi":"10.1109/TALE54877.2022.00136","DOIUrl":"https://doi.org/10.1109/TALE54877.2022.00136","url":null,"abstract":"In order to meet the needs of the country, society and enterprises for high-skilled talents who have mastered the advanced process knowledge of modern microelectronics enterprises and integrated circuit design technology, combined with the innovative concept of \"emerging engineering\", we should actively promote the practice teaching reform of microelectronics and promote emerging engineering. Diversified development of microelectronics professional personnel training. Combined with the innovative concept of \"emerging engineering\", this paper carefully analyzes the new trend of engineering development, the learning characteristics of digital natives, and the problems existing in the practical teaching of microelectronics. Starting from promoting students’ personalized learning, an intelligent learning system is proposed to improve students’ practical innovation ability and explore and cultivate modernization.","PeriodicalId":369501,"journal":{"name":"2022 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130870454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}