Search

The COVID-19 pandemic has changed the entire world, while the impact and usage of online learning environments has greatly increased. This paper presents a new version of the ReaderBench framework, grounded in Cohesion Network Analysis, which can be used to evaluate the online activity of students as a plug-in feature to Moodle. A Recurrent Neural Network with LSTM cells that combines global features, including participation and initiation indices, with a time series analysis on timeframes is used to predict student grades, while multiple sociograms are generated to observe interaction patterns. Students’ behaviors and interactions are compared before and during COVID-19 using two consecutive yearly instances of an undergraduate course in Algorithm Design, conducted in Romanian using Moodle. The COVID-19 outbreak generated an off-balance, a drastic increase in participation, followed by a decrease towards the end of the semester, compared to the academic year 2018–2019 when lower fluctuations in participation were observed. The prediction model for the 2018–2019 academic year obtained an R2 of 0.27, while the model for the second year obtained a better R2 of 0.34, a value arguably attributable to an increased volume of online activity. Moreover, the best model from the first academic year is partially generalizable to the second year, but explains a considerably lower variance (R2 = 0.13). In addition to the quantitative analysis, a qualitative analysis of changes in student behaviors using comparative sociograms further supported conclusions that there were drastic changes in student behaviors observed as a function of the COVID-19 pandemic.

Informal learning in online knowledge building communities (OKBCs) often starts with online academic help seeking, and with visitor inquiries on specific topics. In such a context, learning presupposes adequate OKBC response. Employing a social learning analytics approach based on natural language processing and Bakhtin's theory of dialogism, this study aims to predict blogger OKBC response. Manipulating the blog topic (well-defined vs. ill-defined) and the visitor inquiry format (off-topic vs. on-topic), a field experiment with a 2 x 2 factorial design was conducted on a sample of N = 68 blogger communities with a total of 25,303 members. For the entire sample, the community response was influenced only by the inquiry format. In a separate examination of the experimental groups, however, this remained true only for the well-defined topic, whereas for the ill-defined topic the community response only depended on the previously established dialog quality. The findings suggest identification criteria for responsive communities, which can support newcomer integration in OKBCs and, from a larger perspective, the use of OKBCs as components of formal learning environments.

The paper proposes an approach of enhancing knowledge workers'employability by inducing positive behavioral changes with the aid of current social and semantic technologies. Employability is seen as a psycho-social construct, connected to the development of knowing-how competencies and knowing-whom competencies, by continous learning and a rich social environment. The central element of the approach is a web-based platform - EmployLeaP, which facilitates adults' leap towards a better professional life and gives them the opportunity to find suitable professional e-communities, in which they can learn from their peers and feel appreciated. The recommendation algorithm for finding e-communities is ontology-driven and exploits information retrieved from social connectors anchored in the existent online learning ecosystem. In the same time, during learning within EmployLeaP communities, users' professional visibility is enhanced, by recommending them to job recruiters who also join the platform, in searching competent workers. The badge system used to reward exceptional behaviour within e-communities is the one ensuring users' visibility to recruiters and, in the same, increasing their self-confidence. Preliminary data related to experimental exploitation and perceived usefulness of the platform show promising results of using recent technologies in assisting individuals who want to increase their employability, as well as other stakeholders of knowledge society recruiters or knowledge organizations. We propose a platform to enhance knowledge workers'employability.The web platform targets both learners and recruiters.We use an ontology-based recommendation mechanism for learning communities.The platform was experimentally exploited and positive feedback was registered.An online survey of 391 students showed a high degree of perceived usefulness.

Using online learning communities (OLCs) from the Internet as informal learning environments raises the question how likely these communities will integrate learners as new members, i.e., how integrative these OLCs will be. Such prediction is the purpose of the current study. To achieve this, an identification method of the central, intermediate, and peripheral OLC layers is proposed. Based on the CSCL approaches of voices interanimation and polyphony, an advanced natural language processing framework was employed for dialog analysis in N = 20 integrative vs. non-integrative blog-based OLCs involving 2342 users over one year. Hierarchical clusters built upon communicative centrality reflect socio-cognitive structures including central, intermediate, and peripheral OLC members. The resulting clusters were assigned to the central, intermediate and peripheral community layers with 55–100% consistency, whereas most consistent identification criterion of the socio-cognitive OLC structures was the outdegree centrality, followed by the blog owner inclusion, the numbers of participants, eccentricity and indegree centrality. Subsequently, OLC integrativity was predicted with up to 90% accuracy based on topic complexity, socio-cognitive structure, and automatically assessed dialog characteristics. Consequences for further research and educational practice are discussed.

The study analyzes dialogue in virtual communities of practice (vCoP).Learning analytics are employed in the form of automated content analysis.Significant differences were found between central and peripheral vCoP members.Central participants produced and initiated more dialogue of higher quality.The employed tools appear appropriate for assessing open-ended learning environments. Starting from the socio-constructivist concepts of (virtual) community of practice (vCoP) and internet-based argumentative open-ended learning environments, this study proposes and validates two tools for automated dialogue assessment, ReaderBench and Important Moments, developed on the ground of the polyphonic social knowledge building model. The analyzed corpus was the dialogue produced by an academic vCoP with N=179 community members in 23months, and consisting of 3685 interventions in 292 text-based discussion threads. The analysis results uncovered significant differences in the discussion threads produced by central and peripheral participants, such that central participants produced more interventions with higher collaborative dialogue quality, and the discussion threads they initiated were longer and involved a larger number of participants. Moreover, based on the automated analysis result, the vCoP participants could be classified in two clusters corresponding to the well-known core-periphery structure of CoPs. These findings are consistent with those revealed by other methods, and suggest that the employed tools are appropriate for identifying virtual communities that are appropriate as open-ended learning environments. Further research and development is needed to deepen quantitative vCoP models and test communication strategies recommended to students in vCoP-based argumentative open-ended learning environments.

We developed an educational collaborative filtering recommender agent.We propose a recommendation method for educational materials and tools.Our recommender agent has an integrated learning style finder.The agent produces two types of recommendations: suggestions and shortcuts.The recommender is integrated into a virtual collaborative learning environment. Almost unlimited access to educational information plethora came with a drawback: finding meaningful material is not a straightforward task anymore. Based on a survey related to how students find additional bibliographical resources for university courses, we concluded there is a strong need for recommended learning materials, for specialized online search and for personalized learning tools. As a result, we developed an educational collaborative filtering recommender agent, with an integrated learning style finder. The agent produces two types of recommendations: suggestions and shortcuts for learning materials and learning tools, helping the learner to better navigate through educational resources. Shortcuts are created taking into account only the user's profile, while suggestions are created using the choices made by the learners with similar learning styles. The learning style finder assigns to each user a profile model, taking into account an index of learning styles, as well as patterns discovered in the virtual behavior of the user. The current study presents the agent itself, as well as its integration to a virtual collaborative learning environment and its success and limitations, based on users' feedback.

Participation in virtual communities of practice (vCoP) can be influenced at the same time by technology acceptance and by community factors. To overcome methodological issues connected with the analysis of these influences, learning analytics were applied. Based on a recent vCoP model, the collaborative dialogue comprising 4040 interventions in 1981 messages created by a vCoP located at a US American online university was automatically analyzed. The text-based asynchronous online discussions were scored using a cohesion-based participation and collaboration analysis. Additionally, a sample of N = 133 vCoP participants responded a technology acceptance survey. Thus, a combined research model including the vCoP model and an established technology acceptance model was verified. The results confirmed the vCoP model entirely, and the acceptance model only partially. As consequence for educational research, the CoP model was confirmed and extended to vCoP settings, while the acceptance model appears to need reconsideration. For academic practice, the study initiates the development of assessment tools fostering knowledge sharing through dialogue in vCoP. Also, it suggests how virtual classrooms can be extended to open spaces where value creation takes place through social learning. Learning analytics proved thus successful, provides information that impacts both theory and practice of technology-enhanced learning.

The current study proposes an intelligent approach to compose optimal learning groups in which the members have different domain backgrounds. The approach is based on a well-known evolutionary algorithm - Particle Swarm Optimization. The authors claim that quantifying various indicators, such as background diversity and similarity between the type of interest of the participants, within a group and between groups can positively impact on building learning groups. The algorithm is integrated in an ontology-based e-learning system, designed to create self-built educating communities, in which a trainees goes through the education process, gains points through achievements and ultimately becomes a trainer. When creating a new account, the newly created trainee is asked to self asses himself by filling out a form. The resulting profile is used to assign the user to the most suitable learning group. We propose to assign him by the following rule: maximizing the diversity within a group (due to the fact that multidisciplinary teams are more challenging) and minimizing the diversity between groups (all the groups should have similar composition), meaning a group will have members with similar interests. The study is presented in the context of group building strategies in adults' education.