Automated political campaigns in the digital space can influence electoral votes and tilt the balance of power. We developed a compact ensemble approach named Tiny BotBuster to identify automated bot users, then we ap...
详细信息
ISBN:
(纸本)9783031722400;9783031722417
Automated political campaigns in the digital space can influence electoral votes and tilt the balance of power. We developed a compact ensemble approach named Tiny BotBuster to identify automated bot users, then we applied the Combined Synchronization Index to reveal the political actors working together. We applied our techniques to the 2024 Indonesian Elections, revealing groups of coordinated digital campaigns. We also characterized the coordination-automation interplay, highlighting the use of automation by political parties.
In recent years using autonomous robots for the purposes of loading and unloading objects is highly ubiquitous, especially in the fields of smart-manufacturing and logistics industry. The main purpose of these robots ...
详细信息
ISBN:
(纸本)9783031613524;9783031613531
In recent years using autonomous robots for the purposes of loading and unloading objects is highly ubiquitous, especially in the fields of smart-manufacturing and logistics industry. The main purpose of these robots is to increase the efficiency of product management and thereby increase the productivity in logistics sector. However, with the rapid development of big data, artificial intelligence, machine learning, computer vision and internet of things (IoT), one of the main challenges is to evaluate how these robots interact in unpredictable and uncertain environments. In this paper, the experiments conducted on the iLoabot-M (developed by SENADInc, Shanghai, China) autonomous and loading and unloading robot is described, and how the user interaction is minimized by understanding the behavior analysis over a period of time are evaluated. Initially, system's proto-typing model with the required components such as sensors, actuators, cameras, and other communication and navigation systems is considered for behavior analysis, and then the interaction capabilities are evaluated by assigning specific tasks. The perception system, decision making system, and execution system form the core system components, and results show that they are directly influence the performance in terms of behavior generation, interaction, and task allocation. The behavior analysis is conducted based on different patterns of movements, task-allocation and number of software, hardware, and communication components involved. With this way, users could able to analyze the behavior of the prototype by evaluating the system incrementally within a short time-frame.
Generative AI has become an all-present tool for high school, vocational, and higher education students. Managing the potential of this AI-driven tool is equally important for teachers, as it facilitates ensuring stud...
详细信息
ISBN:
(纸本)9783031679971;9783031679988
Generative AI has become an all-present tool for high school, vocational, and higher education students. Managing the potential of this AI-driven tool is equally important for teachers, as it facilitates ensuring students use it appropriately. This study centers on gathering data from students' perspectives and their interactions with a web-based problem-solving classroom orchestration tool augmented with generative AI capabilities. Results show that students see potential in the use of GenAI for various classroom scenarios. They have a clear understanding of how their peers also use these tools and how it affects their learning process, both positively and negatively. The findings also indicate that students' engagement with AI chatbots integrated into a devoted tool for classroom orchestration enhances their active participation and provides immediate responses to their doubts, in collaboration with teachers who oversee and complement student support during classroom sessions. Additionally, the results highlight the significance of crafting well-formulated prompts to elicit clear and precise responses. Overall, students have positively recognized the utility of the tool for accessing supplementary examples and explanations, which serve as valuable additions to teacher-led orchestration compensating the additional types of teacher supervision needs (e.g. prompts).
The aim of the present study was to evaluate the ability of a robot to conduct cognitive training in elderly people with dementia. Fifty-two institutionalized elderly people were recruited and invited to participate i...
详细信息
ISBN:
(纸本)9783031552441;9783031552458
The aim of the present study was to evaluate the ability of a robot to conduct cognitive training in elderly people with dementia. Fifty-two institutionalized elderly people were recruited and invited to participate in prospective memory training sessions, with or without a robot. They were divided into two equivalent groups in terms of age, level of education and MMSE score. Before and after the intervention phase, neuropsychological assessment was performed on each participant, including several cognitive and non cognitive (self-esteem) evaluations. Moreover, the sessions were recorded in order to compare the interaction behaviors of the 2 groups, using a validated observation grid. Results showed that: 1) the presence of the robot increases the interaction behaviors of the participants during the sessions (such as smiling, laughing, nodding, reaching out to others, talking, etc.);2) That prospective memory training resulted in a significant increase of prospective memory performance, attentional abilities and executive functioning, but this improvement did not differ between the 2 groups These findings confirm the positive impact of a robot as a mediator of cognitive training, but suggest that further research is necessary to determine the effectiveness of these tools, in comparison with traditional training with humans.
The prevalent issue of increased student dropouts, shared by universities worldwide, often culminates in decreased academic performance and prolonged completion times for degree programs. Prompt detection of those stu...
详细信息
ISBN:
(纸本)9783031630309;9783031630316
The prevalent issue of increased student dropouts, shared by universities worldwide, often culminates in decreased academic performance and prolonged completion times for degree programs. Prompt detection of those students facing a likely chance of failing a course could allow universities to intervene with sufficient support and guidance, facilitating an improvement in their performances. Numerous studies have explored the problem of performance prediction from various perspectives using different representations, algorithms, and data sets. The diversity in research strategies, however, complicates comparisons. In this study, we present a thorough evaluation of various predictive algorithms, representations, and predictive targets for the task of predicting student performance across 77 different courses in three distinct programs at the Universidad de los Andes: Systems and computer Engineering, Industrial Engineering, and Economics. The results show that representing data in windows of time spanning 3 previous semesters, in conjunction with the LSTM-based algorithm for binary classification, yields the best results, achieving a precision of 0.838.
Personalized learning paths have become a promising instructional strategy in online learning, as they can cater to individual learners' needs and preferences. However, creating effective personalized learning pat...
详细信息
ISBN:
(纸本)9783031630279;9783031630286
Personalized learning paths have become a promising instructional strategy in online learning, as they can cater to individual learners' needs and preferences. However, creating effective personalized learning paths is a complex task due to the high degree of variability in learners' characteristics, behaviors, and learning contexts. Existing recommendation methods do not adequately address this challenge, as they do not work effectively in dynamic environments. This paper tries to address this gap by proposing a personalized learning path recommendation system using a contextual multi-armed bandit approach to offer a student an optimal learning sequence and provide the student with a modified sequence when re-planning is required.
In-person education has had its fair share of research and best practices developed, however, understanding the educational needs of students enrolled in online courses, specifically needs that are fulfilled by their ...
详细信息
ISBN:
(纸本)9789819742424;9789819742431
In-person education has had its fair share of research and best practices developed, however, understanding the educational needs of students enrolled in online courses, specifically needs that are fulfilled by their instructor, requires further research. Knowing what instructor activities and behaviors support student success can have a confound impact on how instructors teach in the future to improved learning experiences of students. This paper aims at identifying instructor behaviors that impact student success in online courses and that can be supported by data available from online learning platforms. Following the literature, this paper identifies six specific online behaviors of instructors that are expected to increase student satisfaction when completing online courses, which has been related to student overall success. These behaviors include supporting students with their own time management, providing personalized and timely feedback, soliciting feedback from students, being present and actively utilizing the online learning system, encouraging peer to peer interactions, and ensuring students have access to technical support when required. This paper further breaks down these behaviors into specific auditable online activities that can then be further analyzed for their effectiveness in supporting students' success. Such analysis can be extremely valuable in providing evidence-based research to support specific instructor online behaviors that encourage student success.
The academic publishing landscape is rapidly evolving, making quality assessments and impact evaluations of scientific papers increasingly challenging. Understanding the respective methods is crucial for maintaining t...
详细信息
ISBN:
(纸本)9783031724367;9783031724374
The academic publishing landscape is rapidly evolving, making quality assessments and impact evaluations of scientific papers increasingly challenging. Understanding the respective methods is crucial for maintaining the integrity, quality, and relevance of academic publishing in such a changing environment. In this paper, we investigate existing quality-assessment methods for scientific papers, as well as their advantages and disadvantages. For this purpose, we conducted a systematic literature review to capture a comprehensive overview of existing methods, which led to 43 papers and 14 methods. Specifically, we analyze their usage, strengths, and weaknesses, in addition to potential avenues for enhancements. The results can support researchers by providing the knowledge to navigate through quality-assessment methods to make evaluations concerning the reliability and suitability of diverse methods within a specific scientific context.
While Online Learning is growing and becoming widespread, the associated curricula often suffer from a lack of coverage and outdated content. In this regard, a key question is how to dynamically define the topics that...
详细信息
ISBN:
(纸本)9783031723117;9783031723124
While Online Learning is growing and becoming widespread, the associated curricula often suffer from a lack of coverage and outdated content. In this regard, a key question is how to dynamically define the topics that must be covered to thoroughly learn a subject (e.g., a course). Large Language Models (LLMs) are considered candidates that can be used to address curriculum development challenges. Therefore, we developed a framework and a novel dataset, built on YouTube, to evaluate LLMs' performance when it comes to generating learning topics for specific courses. The experiment was conducted across over 100 courses and nearly 7,000 YouTube playlists in various subject areas. Our results indicate that GPT-4 can produce more accurate topics for the given courses than extracted topics from YouTube video playlists in terms of BERTScore.
This study proposes to present the design and face validity of a serious game prototype, Pro(f)Social, as part of a blended learning teacher training program based on social-emotional ethical learning to promote pro-s...
详细信息
ISBN:
(纸本)9783031490644;9783031490651
This study proposes to present the design and face validity of a serious game prototype, Pro(f)Social, as part of a blended learning teacher training program based on social-emotional ethical learning to promote pro-social behavior and well-being among children, through changes in teachers' emotion regulation and moral involvement with cyberbullying and their social-emotional competence to deal with the phenomenon. Teachers are often unaware of aggressive acts among their students, and even when they are, many consider that they are not responsible for resolving cyberbullying issues. Therefore, it is fundamental to develop resources based on human-machine collaboration to attain several milestones in designing serious games to prevent and intervene in cyberbullying by providing teachers with know-how through interactive training with artificial intelligence. The game presented, along with its face validity (n = 290 units for content analysis), offer technology professionals the necessary knowledge to develop future interventions to counter cyberbullying.
暂无评论