17 research outputs found
Data Analytics in Web-based Education in the Higher-education Classroom
No full textAttention span of students in a classroom is very short. To overcome this, different active learning methodologies have been used in the past. Active learning keeps the students busy and engaged throughout the lecture. It breaks the lecture into certain time intervals by intermixing breaks, demonstrations and questions after each interval. For using active learning, clickers and laptops are commonly used in higher education classroom. Most experiments in higher education classroom studying different characteristics of students like learning performance and attention, use clickers and laptop. But, most of these experiments are in a controlled setting, not scalable and compromise the privacy of students. We overcome these problems in an active learning setup in the higher education classroom where we use a web-mediated teaching tool called ASQ. ASQ is a web application that helps to give presentation in a classroom where the presenter has control over the flow of the presentation. ASQ also allows the presenter to interleave the presentation with questions, videos and other interactive JavaScript components. Anyone can anonymously join a presentation in ASQ using a web browser. ASQ tracks the activity of every student interaction by generating event logs each second. In the previous work using ASQ, it has been shown that these logs could be used to infer the attention level of students in the classroom. The goal of this thesis is to gather insights about the fine-grained study behaviour of students in a higher education classroom by analyzing these event logs.We investigate (i) the effect of lecture elements (like the difficulty, relative positioning and spacing of questions; and duration of discussion in the slides) on study behaviour (like attention level, performance and reaction time while answering questions) of students; (ii) the relationship that might exist between attention percentage of students and their participation in the in-class questions; (iii) if students are taking external help when answering questions during the lecture and the relationship that might exist between their tendency to take external help with the difficulty of questions. We conduct our study in a classroom of around 300 students, for 15 lectures in the Web and Database Technology course at TU Delft taught by 2 instructors. We find significant effect of (i) spacing of questions on reaction time and instructor on performance; (ii) length of discussion time associated with a slide on the attention level of students which agrees with past studies; (iii) relative positioning of questions on the performance of students. However, we do not find significant effect of difficulty of questions on performance and reaction time of students while answering these questions. We also find significant effect that students with more attention percentage participate more in the in-class questions. Finally, we find that students take external help while answering questions but the tendency to take external help does not depend on the difficulty of questions
Microstructure and frequency dependent electrical properties of lead-free Na0.5Bi0.5TiO3 perovskite
No full text
Literature Review on Co-Located Collaboration Modeling Using Multimodal Learning Analytics—Can We Go the Whole Nine Yards?
No full textCollaboration is one of the important 21st-century skills. It can take place in remote or co-located settings. Co-located collaboration (CC) is a very complex process that involves subtle human interactions that can be described with indicators like eye gaze, speaking time, pitch, and social skills from different modalities. With the advent of sensors, multimodal learning analytics has gained momentum to detect CC quality. Indicators (or low-level events) can be used to detect CC quality with the help of measurable markers (i.e., indexes composed of one or more indicators) which give the high-level collaboration process definition. However, this understanding is incomplete without considering the scenarios (such as problem solving or meetings) of CC. The scenario of CC affects the set of indicators considered: For instance, in collaborative programming, grabbing the mouse from the partner is an indicator of collaboration; whereas in collaborative meetings, eye gaze, and audio level are indicators of collaboration. This can be a result of the differing goals and fundamental parameters (such as group behavior, interaction, or composition) in each scenario. In this article, we present our work on profiles of indicators on the basis of a scenario-driven prioritization, the parameters in different CC scenarios are mapped onto the indicators and the available indexes. This defines the conceptual model to support the design of a CC quality detection and prediction system.Web Information System
Developing AI into explanatory supporting models: An explanation-visualized deep learning prototype
No full textUsing Artificial Intelligence (AI) and machine learning technologies to automatically mine latent patterns from educational data holds great potential to inform teaching and learning practices. However, the current AI technology mostly works as "black box"-only the inputs and the corresponding outputs are available, which largely impedes researchers from gaining access to explainable feedback. This interdisciplinary work presents an explainable AI prototype with visualized explanations as feedback for computer-supported collaborative learning (CSCL). This research study seeks to provide interpretable insights with machine learning technologies for multimodal learning analytics (MMLA) by introducing two different explanatory machine learning-based models (neural network and Bayesian network) in different manners (end-to-end learning and probabilistic analysis) and for the same goal-provide explainable and actionable feedback. The prototype is applied to the real-world collaborative learning scenario with data-driven learning based on sensor-data from multiple modalities which can assess collaborative learning processes and render explanatory real-time feedback.Web Information System
Association of human interleukin-35 level in gingival crevicular fluid and serum in periodontal health, disease, and after nonsurgical therapy: A comparative study
No full textBackground: Innovating newer methods to diagnose a multifactorial disease such as periodontitis is always challenging for a clinician. Gingival crevicular fluid (GCF) which is closely associated with the periodontal tissue environment has been used a viable alternative to saliva for the diagnosis of periodontitis. Aim: The aim of the present study was to estimate and compare the interleukin-35 (IL-35) levels in GCF and serum among healthy, gingivitis, and chronic periodontitis (CP) individuals as well as to evaluate the effect of nonsurgical periodontal treatment (NSPT) on IL-35 level among patients with CP. Settings and Design: The study was conducted at the Department of Periodontics, Srirama Chandra Bhanja Dental College and Hospital, Cuttack, Odisha, India. It is a comparative study. Materials and Methods: A total of 60 participants were divided into healthy (Group I; n = 20), gingivitis (Group II; n = 20), and CP (Group IIIA; n = 20). GCF samples collected from each individual at baseline and 6 weeks after NSPT for Group III individuals (Group IIIB; n = 20) were quantified for IL-35 levels using enzyme-linked immunosorbent assay. Statistical Analysis: All analyses were performed using Shapiro–Wilk test, analysis of variance, Tukey's honestly significant difference post hoc test, and multiple regression analysis. Results: The mean IL-35 concentration in GCF was significantly high (P < 0.05) for Group IIIA (70.26 ± 4.0 pg/ml), as compared to Group I (54.81 ± 22.3 pg/ml) and Group IIIB (55.72 ± 10.2 pg/ml). Conclusion: In the present study, GCF and serum IL-35 concentration among CP individuals was highest among all the groups. Individuals receiving NSPT showed a significant reduction in IL-35 levels as compared to CP individuals
Association of human interleukin-35 level in gingival crevicular fluid and serum in periodontal health, disease, and after nonsurgical therapy: A comparative study
No full textAI and business management: Tracking future research agenda through bibliometric network analysis
No full textThis study has been designed to analyse the academic landscape of AI on the Scopus and Web of Science (WOS) indices and compare the findings. AI is one of the most prominent and preferred research areas, only a few studies are dedicated to the bibliometric aspect of it. There is a need to compare studies on AI over different databases to identify the impact and usefulness of those studies in decision-making in business management. To conduct this analysis, the authors have collected data from both Scopus and WOS. ‘VOSviewer’, ‘R-Studio’, and ‘MS Excel’ software have been used for performance analysis and science mapping. This is one of the exceptional studies which perform a comparative analysis between two indices and also identifies funding sponsors for support of research in AI. “Dwivedi, Y.K.” is the most productive author and “Huang, Minghui” is the most impactful author. “National Natural Science Foundation of China” is the funding agency which has significantly supported AI research. Technical aspects like “Machine learning”, “neural networks”, and “blockchain” with ‘Sustainability’, ‘sustainable development’, ‘accounting’, and ‘auditing’ are trending themes for managerial decision-making
Towards Collaborative Convergence: Quantifying Collaboration Quality with Automated Co-located Collaboration Analytics
No full textCollaboration is one of the four important 21st-century skills. With the pervasive use of sensors, interest on co-located collaboration (CC) has increased lately. Most related literature used the audio modality to detect indicators of collaboration (such as total speaking time and turn taking). CC takes place in physical spaces where group members share their social (i.e., non-verbal audio indicators like speaking time, gestures) and epistemic space (i.e., verbal audio indicators like the content of the conversation). Past literature has mostly focused on the social space to detect the quality of collaboration. In this study, we focus on both social and epistemic space with an emphasis on the epistemic space to understand different evolving collaboration patterns and collaborative convergence and quantify collaboration quality. We conduct field trials by collecting audio recordings in 14 different sessions in a university setting while the university staff and students collaborate over playing a board game to design a learning activity. This collaboration task consists of different phases with each collaborating member having been assigned a pre-fixed role. We analyze the collected group speech data to do role-based profiling and visualize it with the help of a dashboard
