As the impact of chronic mental disorders increases, multimodal sentiment analysis (MSA) has emerged to improve diagnosis and treatment. In this paper, our approach leverages disentangled representation learning to address modality heterogeneity with self-supervised learning as a guidance. The self-supervised learning is proposed to generate pseudo unimodal labels and guide modality-specific representation learning, preventing the acquisition of meaningless features. Additionally, we also propose a text-centric fusion to effectively mitigate the impacts of noise and redundant information and fuse the acquired disentangled representations into a comprehensive multimodal representation. We evaluate our model on three publicly available benchmark datasets for multimodal sentiment analysis and a privately collected dataset focusing on schizophrenia counseling. The experimental results demonstrate state-of-the-art performance across various metrics on the benchmark datasets, surpassing related works. Furthermore, our learning algorithm shows promising performance in real-world applications, outperforming our previous work and achieving significant progress in schizophrenia assessment.

This study explored the applications of natural language processing techniques on the analysis of storybook to design the storytelling chatbots. Two natural language processing techniques, co-reference and dependency parsing techniques, were applied to process the text of 157 stories books as a means to implement in the invite-narration, positive recognition, follow-up strategies when the chatbot retells the story with the students. The results of the study found that 19 (42%) students demonstrated full narratives which can re-tell the overall story in the storybook, while 22 (49%) students could only retell a simplified story. Affordances and limitations of the use of the two techniques in developing chatbots for reading are discussed.

Schizophrenia is a mental disorder that will progressively change a person's mental state and cause serious social problems. Symptoms of schizophrenia are highly correlated to emotional status, especially depression. We are thus motivated to design a mental status detection system for schizophrenia patients in order to provide an assessment tool for mental health professionals. Our system consists of two phases, including model learning and status detection. For the learning phase, we propose a multi-task learning framework to infer the patient's mental state, including emotion and depression severity. Unlike previous studies inferring emotional status mainly by facial analysis, in the learning phase, we adopted a Cross-Modality Graph Convolutional Network (CMGCN) to effectively integrate visual features from different modalities, including the face and context. We also designed task-aware objective functions to realize better model convergence for multi-task learning, i.e., emotion recognition and depression estimation. Further, we followed the correlation between depression and emotion to design the Emotion Passer module, to transfer the prior knowledge on emotion to the depression model. For the detection phase, we drew on characteristics of schizophrenia to detect the mental status. In the experiments, we performed a series of experiments on several benchmark datasets, and the results show that the proposed learning framework boosts state-of-the-art (SOTA) methods significantly. In addition, we take a trial on schizophrenia patients, and our system can achieve 69.52 in mAP in a real situation.

In this study, we compare the effects of two different pedagogical designs around a computer simulation on students’ scientific literacy in the case of learning science concepts relating to sinking and floating. We also compare the effects of teaching with simulations versus traditional teaching to provide baseline information. A total of 75 eighth-grade students participated in the study. Data collected include the students’ pretest and posttest data that indicate scientific literacy. The results provide evidence for the effectiveness of a student-centered pedagogical design. Reflection and discussion on how to augment the impact of computer simulations are provided.

The purpose of this study was to investigate the relationships between students’ different extent of completion of modeling activity and the students’ modeling competences and learning engagement. Research participants were 76 11-th grade students in Taiwan. The students participated in modeling-based computer simulation activities (MBCSA). We designed and learning patterns was analyzed through lag sequential analysis (LSA). Research instruments included pre- and post-modeling competence tests, engagement questionnaires, and online students’ worksheets. Students’ activity logs were also recorded by the computers. The students’ online worksheets were scored and used for grouping the students into three levels of completion of MBCSA: the Low-Score Group (LSG), Middle-Score Group (MSG) and High-Score Group (HSG). The results showed that, first, in analyzing the students’ pre- and post-modeling competences test, ANCOVA results showed HSG and MSG were significantly higher than LSG on model representation (MR). Second, in analyzing the engagement questionnaires, ANOVA results showed HSG was significantly higher than MSG on positive behavioral engagement and positive social engagement, and LSG was significantly higher than HSG on negative cognitive engagement, negative behavioral engagement and negative social engagement. Third, by using the LSA, six activity patterns were identified in this study. Students in the three groups showed different tendencies of the sequences of completing the modeling activities.

Simulation was found to be an effective tool for learners to learn science. However, young children might have difficulty to integrate their understanding and the simulation because of inability to process virtual and abstract information. This study proposed a sensory simulation which helps young children learn science. The results show that the sensory simulation help the young children assimilation the concept and reflect in some questions while it did not enhance learning in other questions. More qualitative interview data should be collected to understand the cognitive process of using sensory simulation.

With the development of Web technology, a number of collaborative computer simulations are designed to support collaborative problem solving activities. However, studies show that some students often failed to collaboratively solve a problem with collaborative computer simulation. Little research has so far been done to explore the factors why students failed to solve problems with collaboratively computer simulation. The study designed a problem solving activity with collaborative computer simulation and attempted to identify the key factors to a successful learning task by analyzing students’ perceptions on collaborative problem solving. The implication indicated that, with collaborative computer simulation, communication, coordination, mutual support, and effort may be the key factors to solve the problem.

This study attempts to propose a model integrating real videos into the development of simulations on iPads to support students’ science learning about motions based on Predict, Observation and Explanation (POE) framework. Motion examples in videos embedded in the simulation were employed to assist students in contrasting stimulated phenomena and real-world cases for meaning making about force and motion. A preliminary study found that the students, who were given with the video clips, exhibited significantly higher frequencies of modeling (manipulating variables to simulate the movement) and replaying (watching the simulation) than those who were not given with the videos while dealing with complex motion. Such a result suggest that integrating video clips into the simulation could be helpful to stimulate students’ involvements in reviewing and revising the simulation while exploring more complex concepts.

Previous studies show that storytelling is a powerful approach in EFL (English as Foreign Language) elementary classroom because it can facilitate young EFL students to engage in acquisition, provide a rich source of materials, and open communication and interaction possibilities by telling their own stories. In recent years, digital storytelling in a classroom further provides a strategy for teachers to effectively move beyond the print-based texts and engage students in working with digital multimodal texts. Digital storytelling requires students to bring together various modes such as written words, images, and sounds into their own multimodal representations. Recently, many forms of electronic books such as tablet PCs have become available to facilitate English learning and may be applied to implement storytelling activities. Although theories and research support the significance and education value of using digital storytelling, however, empirical studies of using digital storytelling in EFL elementary context is scant because teachers are often overwhelmed by difficulties such as students’ English limited English proficiency, teacher’s pressure of existed curriculum and the lacking pedagogy of using digital storytelling. This study develops digital storytelling pedagogy with iPads to overcome the difficulties and conducts a five-month quasi-experimental study to determine whether digital storytelling pedagogy has the intended effect on participants’ motivation and achievement. Two intact classes (N=32) were randomly assigned as the digital storytelling group and traditional teacher-centered group. Participants’ achievement will be discussed.

Social media on the World Wide Web, such as Wiki, are increasingly applied to support collaborative learning for students to conduct a project together. However, recent studies indicated that students, learning in the collaborative project, may not actively contribute to the collaborative work and are involved only in a limited level of positive interdependence due to the ambiguous ownership on the collaborative work. To this end, this study proposes an approach to support collaborative learning based on the notion of Creative Commons (CC). CC may be helpful to enhance positive interdependency because it provides a mechanism which protects individual creations while encouraging remixing and deriving new creations from them. This study conducted an empirical evaluation to examine how students react to the collaborative learning with CC notions. The results showed that CC can significantly improve participants' attitude to the derivative works, the satisfaction level of remix outcomes, perception to the peer interaction and the sense of work ownership. Such results suggest that CC may be a potential avenue for increasing individuals' responsibilities and motivating them to participate in the collaborative learning activity.

Peer assessment (PA) has been widely adopted in an educational context with ample evidence suggesting the potential to promote learning. We argue that although the process of asking learners to involve in assessing achievement of the others might be a beneficial manipulation for learning, the effectiveness is still unclear for young pupils when creative learning tasks such as storytelling are involved. Creativity self-efficacy might be interfered with peers’ feedbacks. Thus, the presented study proposes an approach to support creativity learning through peer assessment aided by Tablet computers. This study sought a deeper understanding of the relationship between creative self-efficacy (CSE) and creativity product among 54 sixth graders on completing a digital storytelling project. Findings and discussions are included.

Most collaborative mind tools are applied in asynchronous learning contexts. In other words, these tools can support students in joint construction of knowledge through the Internet. However, face-to-face collaborative learning may pose new challenges for the design of collaborative mind tools. For example, without a proper arrangement of learning devices, the control of a mind tool may be limited to a single member and this may reduce willingness on the part of other students to share their personal opinions and this may in turn impede the group learning process. This study has adopted a shared display mind tool combining shared display with a one-to-one learning environment to help students engage in collaborative mind activities. The participants were nine graduate students who enrolled in the course “Learning, Collaboration and Creativity" in a middle-sized university in Taiwan. By analyzing activity logs and video, it was found that the shared display mind tool could facilitate information exchange and sharing. This tool can also help students establish shared visual focus and attract the attention of group members. In addition, it elicits ideas from each individual and inspires new search directions, thus enhancing the elaboration of knowledge for new understanding.

Students' affections in learning have a significant impact on engagement and learning outcomes. When students have negative emotions, they usually do not learn well. But current e-learning systems often lack many features of profound affection, and fail to provide suitable emotional interaction. In this paper, we evaluate some studies of affective interaction e-learning systems. We also proposed our approach to develop an emotionally interactive learning system.

This study applied the features of social media to implement a picture book in facilitating the students collaborative creative activity. Based on Amabile’s componential theory, this study evaluated the influences of social media in students’ creativity behaviors. The results showed that the students were more active to present multi-thinking, as well as revealed higher significant satisfaction in the perceptions of the ownership of working and peers’ mutual support. Moreover, the collaborative creative environment engaged the students in developing creative works.

The internet has been widely used to promote collaborative learning among students. However, students do not always have access to the system, leading to doubt in the interaction among the students, and reducing the effectiveness of collaborative learning, since the web-based collaborative learning environment relies entirely on the availability of computers and the internet. A web-based collaborative learning scheme based on activity awareness carried out through mobile phones is proposed herein. The proposed mechanism automatically sends SMS messages on a GSM network, based on student identity and learning activity, making the student aware of the collaborative learning context, and further improving the student's learning. A web-based collaborative learning activity was implemented in a Taiwan undergraduate class to examine the proposed scheme. Experiments demonstrated that awareness of the collaborative learning context through mobile phones significantly increased student participation in learning activity and improving student learning performance.

Collaborative learning is widely used in classroom activities. The screens of handheld devices, being designed for individual-user mobile application, limit promotive interaction among groups of learners. The small size of screen may lead to fragmented and tete-a-tete communication pattern, and frequently obstacle the externalization of student learning process. This study proposes a shared display groupware with handheld devices in order to support the externalization and articulation of student thinking. The groupware is designed for exploring whether the shared display system in classrooms can augment the handheld devices to promote the student articulation process and communication among participants.

This study proposes the application of the MCSCL groupware for the hearing-impaired students to engage in learning the mathematics word problems. This groupware, which integrates the collaborative argumentation theory, the scaffolding tools, and the comic, is to be applied in the activities of the collaborative learning. We present the system architecture which describes the implementation based on integration of the PDA, the network technology, and the learning strategy. Furthermore, this study employed the groupware as a channel for the hearing-impaired students to improve the experience of learning the mathematics word problems.

This study presents a negotiation-based e-learning framework to promote learning motive and enhance the interaction between learners and instructors. In terms of learning communication, a fuzzy constraint-based agent negotiation mechanism is proposed as a flexible model to suggest pedagogies or learning strategies. Examples are provided to illustrate the proposed framework for constructive and collaborative learning.

Technologies gradually take part in pedagogical progress, and some play a role as a mediating object. In this study, we construct a system to help teachers easily apply peer instruction (PI) and just-in-time teaching (JiTT) pedagogical models. After having a pilot experiment which adopts PI and JiTT on general physics course with freshmen at the department of electrical engineering, we found two problems. One is pre-class assignments participation rate, and the other is in-class process issue. Therefore we designed a pedagogical method, named think-individually-then-peer-share (TIPS), to deal with these two problems.

Users still have frustrations when they use traditional search engines on learning Web. In order to effectively retrieve relevant students' documents while searching, this study proposes a portfolio search engine based on personal construct. The database source succeeds the students' portfolios of our previous system on Web. The experimental results show that the performance of portfolio search engine is always better than traditional search engine significantly. Besides, the Bayesian belief network mechanism can be used for assisting this portfolio search engine to promote the efficiency of performance.

We utilize Web and database technology to construct a journal based portfolios assessment system to realize a legitimate peripheral participation (LPP) (J. Lave et al., 1990) learning community. In the system, we divide system into three layers, the view layer presents data by the Oracle Portal Server, the data layer stores data by the Oracle Database Server and the operating control layer operates workflow by the Oracle Database trigger. Job data analysis and a questionnaire indicates that the Web Journal is effective to promote knowledge exchange. Students can improve learning performance and it can form a LPP structure. The purpose of using the journal approach [Roth, W.M. (1997)] is to emulate the forming of academic societies formed by journals. At the same time, the achievement of students in a course is based on their publications in journals and the positions they played in the journals. First, students submit their work such as homework, learning portfolios, reports of organizing contents in the discussion, learning problems, related Web sites. Each submitted article would be assessed by three peers. Then the reviewers will review the submitted works. The reviewers will give comments to students. The journal system will publish good articles. Articles published include submitted works and reviewer's comments hoping that students will contribute and exchange their knowledge.

This study attempted to reuse the web learning portfolios to scaffold problem solving for activating students' Zone of Proximal Development. First, we analyzed cases from students' learning portfolios for getting case knowledge and student ability, and then used case based reasoning technology for recommending cases to students. After students referred these cases, we adopted data mining technology and issue-based information system to analyze the match model between students and cases. Finally, we constructed an online case based learning system, which could retrieve and reuse the fitting cases to effectively scaffold problem solving on student learning process.

Web based peer assessment for portfolios has been used as an innovative assessment methods to reuse students portfolio for refining learning. However, without sophisticated support to articulate the assessment contexture about portfolios, students cannot communicate with explicit learning concepts and think reflectively for refinement of their learning. This study attempts to utilize knowledge acquisition and data mining techniques to solve the problems in support contexture awareness. By way of knowledge acquisition and data mining techniques, web peer assessment systems obtain students' personal theories during assessing portfolios. Thereby, teachers and students can go online to fully exchange personal theories, thus allowing them to think reflectively for refinement of learning.

Owing to the lack of face-to-face interactions, students using a web-based learning system are likely to study alone and with relatively little classmate support and pressure. Teachers in a web-based learning system may apply the group-learning model to overcome this problem. Therefore, teachers first need to organize, manage, and monitor the group learning. Additionally, they must take appropriate actions based on teaching strategies to improve the learning achievements of the students. To perform these tasks effectively, the teachers must obtain relevant information by searching and analyzing the huge amount of web-access logs or by monitoring web interactions. This will be burdensome and difficult to do well for the teachers. This work presents novel methodologies for developing instruments to assist teachers in performing grouping, intervention and strategy analysis. The proposed methodologies apply data mining tools provided by existing database management systems. A tool is initially R developed to assist in organizing learning groups according to teacher specifications. Database techniques, including multidimensional cube, are then applied to make student web logs meaningful and helpful to teachers in managing group learning. The associate rule mining tool is finally employed to assist teachers in analyzing their pedagogical strategies. These tools relieve the teacher of tedious data collection and analysis, and thus can focus on managing the groups to promote student learning achievement.

As database and workflow technologies are used to manage business processes, decision-makers of enterprises must query the execution of business processes to understand and refine these processes for expected throughput and quality. Introducing the representation of business processes in the database schema allows the execution histories of business processes to be maintained in the database for supporting queries on how business processes are executed. In this work, we incorporate finite state machines into the entity-relationship (ER) model for representing business processes in the database schema. Analytical systems can be developed in the proposed representation to assist decision-makers in observing the business processes.

Existing temporal databases focus on the management of data history. However, it may be required to know how users, procedures and policies affect the data value changes in decision support system and database debugging or maintaining systems. If so, the object model needs to incorporate the behavioral modeling of data objects. We propose a model using finite state machines, method signatures and a method invocation network to model the behavior between objects. A type system is also devised to enforce the substitutability of subtype objects in the class inheritance hierarchy. A decision maker or database application developer can query the effect of events by using the proposed object model.

In order to manage the history of objects in a database, some researchers have proposed temporal database systems. However, data change is always caused by the behavior of objects. A database application may not only need the data history of objects but also the behavioral history of objects. Current temporal databases only consider the data history of objects but do not take the behavioral history of objects into account. The purpose of this paper is to extend the capability of current object-oriented databases so that they can manage the data history and behavioral history of objects. The paper discusses a data model, query language and a storage system. A prototype system is developed on the Gemstone object oriented database system.