This paper presents the research outcome, Authorship Forensics Portal, leveraging both Statistical Natural Language Processing (SNLP) and Convolutional Neural Networks (CNN) techniques to differentiate documents written by humans and ChatGPTs. The portal allows teachers to (1) upload labeled data that contains written text and its author; (2) configure parameters that are required for training models, e.g., 2-class (i.e., human and ChatGPT) or 3-class (i.e., human, ChatGPT 3.5, and ChatGPT as well as the train/test set split ratio, validation set ratio, and validation accuracy threshold for stopping the training process; (3) review the details of a trained model, e.g., the train/test set, the time spent, the prediction results like numbers, true positive, false positive, precision, recall, and f-value, etc.; (4) make their own trained models be private so only themselves can see and use or be public so other teachers can also see and use; and, (5) ask a chosen trained model for its opinion on whether a piece of text written by human or generative Al (e.g., ChatGPT for 2•class prediction and ChatGPT 3.5 or ChatGPT 4 for 3-class prediction). The results demonstrate a significant ability of the models to distinguish between human and Al-written text, with highest precision 0.9868 (Fo_5 score 0.9647) for the 2-class (human and ChatGPT) testing subset and highest precision 0.9875 (Fo.5 score 0.9753) for the 3-class (human, ChatGPT 3.5, and ChatGPT 4) testing subset.

The International Conference on Advanced Learning Technologies (ICALT) is an annual conference organized by the IEEE Computer Society and IEEE Technical Community on Learning Technology. It aims to bring together people who are working on the design, development, use, and evaluation of technologies that will be the foundation of the next generation of e-learning systems and technology-enhanced learning environments. After its kick-off as IWALT in Palmerston North, New Zealand (2000), ICALT has been held in Madison, USA (2001), Kazan, Russia (2002), Athens, Greece (2003), Joensuu, Finland (2004), Kaohsiung, Taiwan (2005), Kerkade, The Netherlands (2006), Niigata, Japan (2007), Santander, Spain (2008), Riga, Latvia (2009), Sousse, Tunisia (2010), Athens, Georgia, USA (2011), Rome, Italy (2012), Beijing, China (2013), Athens, Greece (2014), Hualien, Taiwan (2015), Austin, USA (2016), Timisoara, Romania (2017), Mumbai, India (2018), Maceió, Brazil (2019), Tartu, Estonia (2020, Online), and Virtual (2023, Online) due to the COVID-19 pandemic, Bucharest, Romania (2022, Hybrid). The 23nd IEEE International Conference on Advanced Learning Technologies (ICALT 2023) is organized by IEEE TCLT and held in Orem, Utah, United States, in a hybrid model due to the pandemic.

With the rising popularity of Object-Oriented Programming (OOP) in both research and industry, it is important that computer science students be educated in the fundamentals of OOP and what it can be used for. However, OOP can be difficult for students to learn because of the complex interactions between objects and code. We believe that implementing a web-based programming tutorial system alongside traditional instruction may help students to better understand the fundamental principles of OOP and avoid common programming misconceptions.

Propositional logic is a fundamental concept in Computer Science. However, some students are struggling with connecting natural language statements and propositional logic. This research designs an escape room computer game that requires players to interpret the logic statements to escape the room. This paper presents a pilot user study to test the usability of the environment. This study shows that students believe the game is a good environment for learning. Moreover, students who like or dislike playing computer games give the same score in system usability, showing that students' attitudes toward computer games does not affect their given score in system usability.

Propositional logic is part of foundational concepts of computer science. However, many students confuse between IMPLICATION and EQUIVALENCE. Further, the students are persistently under the impression that they have mastered the basic logical concepts. We developed an educational game to engage the students' interest in learning basic logical concepts. We developed a virtual escape room where is given logical hints to help them escape. While the hints are always correct, when asked students who confuse IMPLICATION and EQUIVALENCE answer incorrectly. This will familiarize them with the idea that IMPLICATION and EQUIVALENCE.

This research evaluated an annotation recommendation system – GRACE (General Rapid Annotation Clustering Enhancement) – which gives suggestions of what annotations might be missing when students were reading the teaching materials. A pilot is done in two computer science classes in a college in Tunisia. The results show that system’s usability is acceptable for students doing online reading activities on GRACE.

Although educational games have been proved to be useful to get students motivated in doing learning activities, one of the most attractive game feature – farming – has rarely taken into consideration while designing and assessing an educational game. In this research, we design and develop the farming feature, also known as player versus environment (PvE) subsystem, for an educational game platform MEGA World (Multiplayer Educational Game for All). We discuss the operation workflow that the PvE subsystem communicates with MEGA World main system and design correspondent mechanic and required modules to assist students’ learning. The subsystem has two game modes and the students can use the knowledge or skills they have learned in the course to fight with the monsters and earn the rewards. We expect this subsystem can improve students’ learning motivation and performance. In order to verify our expectation, we design a semester-long experiment that involves four groups of undergraduate students.

In order to fit students' needs, an accurate computer game attitude scale is needed so teachers and researchers can know among their students who can really benefit from the use of educational games. In this paper, the research team analyzes 218 students' responses of a revised computer game attitude scale and finds their computer game attitude relationships and differences among gender, grade, preferred gaming way and game playing experience.

Worksheet is a common tool for teachers guiding students learning a subject. This research designs an automatic worksheet generator for constructing a worksheet according to the results of student's online exam. We focus on the worksheet of botany observation and analyze 47 different activities in the worksheet. The relation between the worksheet activity and its cognitive ability can be used to decide what activity should be constructed based on students' test result. A simple example is demonstrated in the end of this paper.

Mobile Learning makes students get the advantages of both traditional learning and e-learning. How to give students learning sequence suggestions in the mobile learning environment is a big issue and is also the goal of this paper. This research uses knowledge map to store the characteristics of each learning object and designs a situated map to represent spatial knowledge in the mobile learning environment. By using these two knowledge structures, knowledge map and situated map, the system created by this research can generate various navigation sentences and ask students to observe the characteristics of learning objects. This research also takes information theory into consideration in order to decide which navigation sentence should deliver to the student first. The system calculates the entropy for each generated sentence and finds the most appropriate one to deliver to the student. At the end of this paper, an experiment system is implemented for the 5th year biology course, Plant Observation.

The Broadcast Over Remote Guide System (BORGS) is a web based system that supports teachers to synchronously broadcast the global web pages and other electronic files to students.

This paper designs a learning notification express delivery service for providing students information about their learning status, their next learning activities, and even reminder notes. The learning notification express delivery service uses Petri-net for modeling learning activities. In order to make students knowing what status they are and what activities they need to do during the learning process, a learning planner is also developed to make teachers feel more comfortable in planning their teaching schedule.

This paper proposes the architecture of learning companion agent with facial expression of emotion. Based on ABC and ToK architecture, the emotion agent architecture contains five modules to realize the interaction in the world. A particular part of this research is the transition between emotion space in emotion module and facial expression space in facial expression module. Using this transition and those five modules, a small experiment Web site with emotion agent demonstrates the facial expression of the agent and its emotion tracks.

We implement an instructional system, called Internet virtual community (IVC for short), according to the instructional model of the Problem-Based Internet Assisted Learning System (PBIALS for short), a previous research result based on the problem-based learning (PBL for short) theory. In order to achieve the instructional model of the PBIALS, four phases are developed for the instructional process include the phase school I - III and the phase outside school. To ensure the instructional system is work and useful, a teaching unit - Dream Computer - is constructed for the basic computer concept I, the first year course of the information program in Chi-Ping vocational school, Taiwan. A self designed questionnaire is also used for collecting the feedbacks responded from the students and evaluating the instructional model/process/system proposed by us.

We propose a methodology to calculate both the difficulty of the basic problems and the difficulty of solving a problem. The method to calculate the difficulty of problems is according to the process of building a problem, including concept selection, unknown designation, and proposition construction. Some necessary measures observed in the problem building process are also defined in order to formulate and calculate the difficulties. Beside the difficulty of the basic problem, four difficulty dimensions, identification, elaboration, planning, and execution, corresponding to the problem solving steps are also analyzed. With these difficulty measures learners can understand what kinds of problems they met and what sorts of problem solving strategies are emphasized in solving the problem. To reach our goal, an item generating system is constructed for demonstrating and supporting the difficulty calculation.

To build an interactive mechanism for a distance learning environment such as a scientific experiment, the architecture of the learning environment and assisting agents should be taken into consideration first. Another issue for constructing an interactive mechanism is the protocols between the environment and the agents. An experiment action language is designed for this purpose. In addition, a method for agents to infer rules is also presented in this paper.