Computers & Education最新文献

Self-regulated learning (SRL) can be defined as the ability of learners to act independently and actively manage their own learning process. This skill becomes especially important in online environments, which allow learners to decide where and how to study. Most research on SRL has focused on students; few studies have addressed teachers' SRL as learners, and only a handful has done so in the context of online learning. A better understanding of teachers' SRL is essential since teachers are expected to support the development of their students' SRL abilities. This study contributes to bridging this gap by examining how online learning patterns reflect the self-regulated learning of teachers as learners in an online professional development (PD) course on nanotechnology. The study applies a mixed methods approach that combines the qualitative analysis of interviews with teacher learners and a personal summary of their learning process represented in four vignettes as well as quantitative log-file analysis to identify teachers' learning patterns. The patterns identified are interval learning, on-track learning, skipping difficult parts, concentrated learning toward the end of the course (i.e., “bingeing”), and watching together. These patterns indirectly shed light on teachers' SRL skills, especially their time management and task strategies, demonstrating that there is no one-size-fits-all approach to learning. The study highlights the need for a holistic approach, provides deeper insights into teachers’ learning experiences, and helps design future online PD courses.

As no study has systematically theorized and empirically tested an ecological model of students' cooperative behaviors during game-based learning, this study moves toward doing so by modeling multiple levels of antecedents of students' prosocial behaviors during game play. Specifically, we propose a theoretical model of how player personality, players’ personality composition, and recent sequences of strategies or game moves affect the likelihood of prosocial behavior in each turn of talk. Then, we empirically tested our model on 8432 turns of talk by 17 adolescents in eight face to face games via statistical discourse analysis.

Players who were agreeable, conscientious, and patient showed prosocial behaviors more often. Meanwhile groups with only one agreeable person, only one extrovert, or only one conformist showed fewer prosocial behaviors. Furthermore, recent strategies such as advise, lend resources, or consent were more likely to precede a prosocial behavior. By contrast, recent aggressive moves reduced the likelihood of an immediate prosocial behavior. For example, a sequence of consecutive attacks sharply reduced the likelihood of a prosocial behavior. Furthermore, interactions among these attributes also affected the likelihood of prosocial behaviors.

These results contribute to and help integrate social identity theory and social learning theory by moving toward an ecological explanatory model with player personalities, player composition, sequences of strategies and game moves, and their interactions. These insights (a) help bridge the gap in our understanding of how students act and react in strategic activities, and (b) inform game design and instructional practices seeking to foster prosocial behaviors and environments.

In video lectures, instructors often use spontaneous emotional expressions (facial expressions, tone of voice) and visual cues (underlining, circling) to guide students' attention toward key instructional information. While previous research has confirmed the benefits of visual cues in guiding attention and processing specific information, there's a notable gap in understanding the role of emotional expression in this context. Moreover, there is a lack of comprehensive exploration regarding the specific design of both behaviors (whether they emphasize the same instructional information) and their effect on students. This study conducted two experiments. Experiment 1 first confirmed the guiding effect of an instructor's emotional expression on students, establishing the foundation for our research. Additionally, Experiment 1 explored the impact of the consistency/inconsistency of facial expressions and tone of voice, including student motivation, cognitive load, and learning performance. Results revealed the benefits of consistent positive emotional expressions on motivation and transfer performance, and the benefits of consistent negative emotional expressions on retention performance. Furthermore, we found that tone of voice was a key factor in guiding students, while facial expressions were associated with students' immediate memory. Building upon Experiment 1, Experiment 2 introduced visual cues to investigate the combined impact of these two guiding behaviors on students. Results regarding emotional expressions were replicated, confirming the positive effects of both. Moreover, we found that the irrelevance of visual cues weakened the guiding influence of emotional expression on students, leading to the loss of relevant information. Therefore, we suggest encouraging instructors to convey positive emotions to enhance the learning experience while emphasizing key information through negative emotional expressions accompanied by visual cues. Additionally, minimizing or concealing visual cues whenever possible is advisable when delivering content beyond visual representations.

In massive open online course (MOOC) discussion board, students' learning experience, reflecting implicit cognitive and affective states, is related to their learning outcomes and course's completion rates. The majority of researches about learning experience identification in MOOCs depend on post-hoc questionnaires, which may encounter issues such as personal biases, hazy memories, or time constraints, and distribution difficulty in MOOCs. Moreover, learning experience is influenced by students' interactions during learning but their relationship has not been thoroughly explored. This study aimed to address these issues. Firstly, it proposed an artificial intelligence-based text analysis approach for automatically identifying patterns of learning experiences from the large-scale students' posts in MOOC discussion board. It had performance advantage in terms of accuracy when compared with the other competing approaches. Secondly, this study defined students' interactive roles from both social relations and interaction behaviors in MOOC discussion board, and analyzed learning experiences corresponding to the different interactive roles. For students with high participation and low influence in interactions, flow and boredom were prone to happen, while for students with low participation and high influence in interactions, anxiety and apathy were easy to generate. Finally, this study revealed the effect of learning experience on learning achievement with respect to interactive role. For students with high participation characteristics, their learning achievements were less affected by learning experience, while for students less active in interaction, flow was related with good learning achievements. In summary, this study had significant methodological implications for automated learning experience identification. Moreover, this study revealed importance of interactive role in describing the interplay between learning experience and learning achievement, and provided suggestions for the improvement of MOOCs.

Artificial intelligence (AI) has been hailed for its potential to revolutionize teaching and learning practices. Undoubtedly, there has been development, but has it transferred to a new pedagogical trend? Indeed, research shows more tools, software, etc., built through AI, but there is still a limited understanding of its pedagogical impact. This review aims to assess whether AI has indeed led to new pedagogical trends in education using a Human Center AI framework. To accomplish this, a systematic review of research on the pedagogical applications of AI in K-12 contexts was conducted, following the PRISMA guidelines. The review involved an inductive coding analysis of a comprehensive search across WoS, Scopus, and EBSBU. From a pool of 3277 publications spanning 2019 to 2023, 183 papers met the inclusion criteria for detailed analysis. Six categories emerged: Behaviorism, Cognitivism, Constructivism, Social Constructivism, Experiential Learning, and Community of Practices. The findings of this research provide a promising perspective on synthesizing the results based on the pedagogical framework that describes AI implementation. While technological advancements have improved AI capabilities, the application of AI in education largely follows the same principles of previous technologies. This research suggests that the failure to transform education through AI stems from a lack of consideration of Gardner's proposed ninth intelligence type—pedagogical intelligence. Furthermore, this paper offers a critical analysis of the HCAI framework and proposes an adaptation called Pedagogical Centered AI (PCAI) for designing and using AI in K-12 education. Final discussions highlight the implications and future perspectives of AI in educational settings.

Several challenges exist in computer-supported collaborative learning environments, such as the potential for distraction and student boredom and isolation, which may adversely affect the quality of collaborative learning and knowledge construction. On the other hand, as an innovative learning tool, physical robots are seen as successful collaborative learning facilitators that can raise student engagement, strengthen social presence, and boost learning results. Meanwhile, tasks designed based on Bloom's taxonomy further ensure students' attention and cognitive growth in robot-supported collaborative learning (RSCL) environments. Although some researchers have explored how to maintain engagement in previous studies on robots, it is still difficult due to the lack of a commonly employed annotation method for evaluating engagement. Therefore, this study proposed the interactive, constructive, active, passive, and behavioral (ICAPB) engagement coding model, combining cognitive and behavioral engagement, to comprehensively analyze the relationship between pre-knowledge, student engagement, and learning achievement in the RSCL environment. An experiment was conducted in a first-aid course at a university to evaluate the effectiveness of this approach. The study involved a total of 36 students using a collaborative robotic system with Bloom's taxonomy. The results showed that pre-knowledge, whether at a high or low level, did not significantly affect students' posttest scores. Instead, student engagement significantly positively impacted their learning achievement.

With the prevalence of generative AI tools like ChatGPT, automated detectors of AI-generated texts have been increasingly used in education to detect the misuse of these tools (e.g., cheating in assessments). Recently, the responsible use of these detectors has attracted a lot of attention. Research has shown that publicly available detectors are more likely to misclassify essays written by non-native English speakers as AI-generated than those written by native English speakers. In this study, we address these concerns by leveraging carefully sampled large-scale data from the Graduate Record Examinations (GRE) writing assessment. We developed multiple detectors of ChatGPT-generated essays based on linguistic features from the ETS e-rater engine and text perplexity features, and investigated their performance and potential bias. Results showed that our carefully constructed detectors not only achieved near-perfect detection accuracy, but also showed no evidence of bias disadvantaging non-native English speakers. Findings of this study contribute to the ongoing debates surrounding the formulation of policies for utilizing AI-generated content detectors in education.

The efficacy of well-designed instructional videos for STEM learning is largely reliant on how actively students cognitively engage with them. Students' ability to actively engage with videos likely depends upon individual characteristics like their prior knowledge. In this study, we investigated how digital trace data could be used as indicators of students' cognitive engagement with instructional videos, how such engagement predicted learning, and how prior knowledge moderated that relationship. One hundred twenty-eight biology undergraduate students learned with a series of instructional videos and took a biology unit exam one week later. We conducted sequence mining on the digital events of students' video-watching behaviors to capture the most commonly occurring sequences. Twenty-six sequences emerged and were aggregated into four groups indicative of cognitive engagement: repeated scrubbing, speed watching, extended scrubbing, and rewinding. Results indicated more active engagement via speed watching and rewinding behaviors positively predicted unit exam scores, but only for students with lower prior knowledge. These findings suggest that the ways students cognitively engage with videos predict how they will learn from them, that these relations are dependent upon their prior knowledge, and that researchers can measure students’ cognitive engagement with instructional videos via mining digital log data. This research emphasizes the importance of active cognitive engagement with video interface tools and the need for students to accurately calibrate their learning behaviors in relation to their prior knowledge when learning from videos.

Based on the assumptions of Cognitive Load Theory and its derived signaling principle, previous research on instructional material has mainly investigated the effect of including visual cues to support the processing and integration of information. In the context of the renewed interest in commented videos and podcasts as instructional materials, the present study investigates the influence of prosodic signals on learning with digital media. An online experiment was conducted with 102 German students using an audio podcast as digital learning material. The audio recording was varied following the prosody of human language in terms of a 2 (volume: regular vs. higher) × 2 (pace: regular vs. slower) between-subject design to examine signaling key concepts. The results showed a positive effect of both prosodic cues manipulations (main effects) on learning outcomes and the most substantial impact when cumulated. This aligns with previous research on visual cues and thus extends findings on the signaling effect to the auditory modality. However, the picture is not so clear-cut. Indeed, higher learning outcome was also associated with higher mental effort and load with higher volume and no difference in effort but a lower load for a slower pace. Further, the presence of signals was also paired with an underestimation of learning. Overall, this could indicate a difficulty in processing the prosodic cues and integrating the signaled elements in the mental model, with an unknown effect on longer-term learning. Future research could further investigate additional possibilities of prosody (e.g., neutral vs. euphoric tone) as prosodic cues and characteristics linked to the speaker (e.g., age, gender) in podcasts and multimedia documents.

Social media has become an integral part of youth's daily lives. Though it brings many benefits such as creative self-expression and opportunities for social connection and support, studies have revealed that exposure to cyberbullying, misinformation and disinformation, or phishing and scams pose great risks to youth's mental health and long-term development. There is no lack of education programs designed to teach youth media literacy, but very few offer experiential learning environments to support youth's development of social media literacy. Youth learners' engagement patterns and learning outcomes in such environments remain unknown. This study seeks to fill in this gap by examining how learners' engagement patterns predict learning outcomes (social media literacy) in a simulated environment that embodies the core components of experiential learning. Two types of data were collected from: 1) n = 150 youth participants in a controlled environment (“data from the classroom”), and 2) n = 3552 participants on the internet (“data in the wild”). The findings revealed learners' engagement patterns (e.g., time spent, completion rate of actions etc.) in different phases of experiential learning, and highlighted the importance of active participation (taking recommended actions instead of passively viewing the course content) in predicting better learning outcomes. This study contributes to understanding the relationship between learners' engagement patterns in experiential learning environments and their knowledge outcomes in social media literacy, and offers practical implications for the improvement of instructional design to enhance experiential learning.