Karen Stepanyan

A Social Network Analysis Perspective on Student Interaction within the Twitter Microblogging Environment

This paper summarises the analyses of participant interaction within the Twitter microblogging environment. The study employs longitudinal probabilistic social network analysis (SNA) techniques to identify the patterns and trends of network dynamics. It explores the associations of student achievement records with the observed network. The results indicate tendencies towards: [i] reciprocal interaction, and [ii] adoption of a selective approach in communication over time, implying that students tend to communicate with fewer peers over time. The evaluations that examine achievement score attributes indicate [iii] network homogeneity and popularity effects associated to achievement scores – suggesting greater interaction among students of similar levels and more attention to higher achieving students.

Who students interact with? a social network analysis perspective on the use of twitter in language learning

This paper reports student interaction patterns and self-reported results of using Twitter microblogging environment. The study employs longitudinal probabilistic social network analysis (SNA) to identify the patterns and trends of network dynamics. It is building on earlier works that explore associations of student achievement records with the observed network measures. It integrates gender as an additional variable and reports some relation with interaction patterns. Additionally, the paper reports the results of a questionnaire that enables further discussion on the communication patterns.

Social Personalized Adaptive E-Learning Environment: Topolor - Implementation and Evaluation

This paper presents a quantitative study on the use of Topolor - a prototype that introduces Web 2.0 tools and Facebook-like appearance into an adaptive educational hypermedia system. We present the system design and its evaluation using system usability scale questionnaire and learning behavior data analysis. The results indicate high level of student satisfaction with the learning experience and the diversity of learning activities.

Culture, role and group work: A social network analysis perspective on an online collaborative course

This paper discusses the patterns of network dynamics within a multicultural online collaborative learning environment. It analyses the interaction of participants (both students and facilitators) within a discussion board that was established as part of a 3-month online collaborative course. The study employs longitudinal probabilistic social network analysis (SNA) to identify the patterns and trends within the network. It conjectures and tests a set of hypotheses concerning the tendencies towards homophily/heterophily and preferential attachment. The paper presents identified interaction network patterns in relation to cultural differences. It also evaluates network dynamics by considering participant roles and group work in the course under study. Results of social network analyses are reported along with measures of statistical confidence in findings. The potential for extending exploratory SNA methods and visualisation techniques in educational research are discussed here.

It's all in the content: state of the art best answer prediction based on discretisation of shallow linguistic features

This paper addresses the problem of determining the best answer in Community-based Question Answering websites by focussing on the content. Previous research on this topic relies on the exploitation of community feedback on the answers, which involves rating of either users (e.g., reputation) or answers (e.g. scores manually assigned to answers). We propose a new technique that leverages the content/textual features of answers in a novel way. Our approach delivers better results than related linguistics-based solutions and manages to match rating-based approaches. More specifically, the gain in performance is achieved by rendering the values of these features into a discretised form. We also show how our technique manages to deliver equally good results in real-time settings, as opposed to having to rely on information not always readily available, such as user ratings and answer scores. We ran an evaluation on 21 StackExchange websites covering around 4 million questions and more than 8 million answers. We obtain 84% average precision and 70% recall, which shows that our technique is robust, effective, and widely applicable.

Student Engagement with Peer Assessment: A Review of Pedagogical Design and Technologies

The paper summarizes participatory action research that explores student attitudes towards a peer assessment exercise and further reveals a distinctive pattern in student responses. A formative and reciprocal peer assessment exercise was studied to identify possible reasons for low levels of student participation. The target group included students in an undergraduate course in computing. A follow-up questionnaire, undertaken by 36 students, was analyzed and compared against assignment marks. Finally, the access statistics of the virtual learning environment (VLE) were examined. The major results indicate the following: [i] an expectation of more explanatory and supportive tutor intervention; [ii] a student preference towards anonymity; [iii] student interest in accessing peer work; and [iv] that the allocation of marks and in-class activities factors are important in encouraging student involvement.

Evaluation of Social Interaction Features in Topolor - A Social Personalized Adaptive E-Learning System

Here we present a case study that analyzed the social interaction features in Topolor, an adaptive personalized social e-learning system. This paper focuses on the evaluation of the perceived usefulness and usability. The results show a considerably high satisfaction of the students. We discuss the evaluation results and outline the further improvement plan.

Technological foundations of the current blogosphere

In this paper, we review the technological foundations of the current Blogosphere. The review is primarily based on a large-scale evaluation of active blogs. The extensive list of examined technologies enables commenting on a range of widely adopted standards and potential trends in the Blogosphere. The evaluation has been conducted in the following stages: 1. Retrieving and parsing a large set of blogs 2. Identifying and quantifying the use of technologies such as web standards, adopted services, file formats and platforms. 3. Analysing collected data and reporting the results 4. Comparing the results with existing findings from the generic Web to identify similarities and differences in the Blogosphere. The presented work was performed as part of BlogForever (ICT No. 269963), an EC funded research project aiming to aggregate, preserve, manage and disseminate blogs. The results of this study are relevant within the context weblog preservation and weblog data extraction.

Entropy-based automated wrapper generation for weblog data extraction

This paper proposes a fully automated information extraction methodology for weblogs. The methodology integrates a set of relevant approaches based on the use of web feeds and processing of HTML for the extraction of weblog properties. The approach includes a model for generating a wrapper that exploits web feeds for deriving a set of extraction rules automatically. Instead of performing a pairwise comparison between posts, the model matches the values of the web feeds against their corresponding HTML elements retrieved from multiple weblog posts. It adopts a probabilistic approach for deriving a set of rules and automating the process of wrapper generation. An evaluation of the model is conducted on a collection of weblogs reporting a prediction accuracy of 89 %. The results of this evaluation show that the proposed technique enables robust extraction of weblog properties and can be applied across the blogosphere.

A hybrid approach for spotting, disambiguating and annotating places in user-generated text

We introduce a geolocation-aware semantic annotation model that extends the existing solutions for spotting and disambiguation of places within user-generated texts. The implemented prototype processes the text of weblog posts and annotates the places and toponyms. It outperforms existing solutions by taking into consideration the embedded geolocation data. The evaluation of the model is based on a set of randomly selected 3,165 geolocation embedded weblog posts, obtained from 1,775 web feeds. The results demonstrate a high degree of accuracy in annotation (87.7%) and a considerable gain (27.8%) in identifying additional entities, and therefore support the adoption of the model for supplementing the existing solutions.