Newcomer Integration in Online Knowledge Communities: Exploring the Role of Dialogic Textual Complexity

Using online knowledge communities (OKCs) as informal learning environments poses the question how likely these will integrate newcomers as peripheral participants. Previous research has identified surface characteristics of the OKC dialog as integrativity predictors. Yet, little is known about the role of dialogic textual complexity. This contribution proposes a comprehensive approach based on previously validated textual complexity indexes and applies it to predict OKC integrativity. The dialog analysis of N = 14 blogger communities with a total of 1937 participants identified three main components of textual complexity: dialog participation, structure and cohesion. From these, dialog cohesion was higher in integrative OKCs, thus significantly predicting OKC integrativity. This result adds to previous OKC research by uncovering the depth of OKC discourse. For educational practice, the study suggests a way of empowering learners by automatically assessing the integrativity of OKCs in which they may attempt to participate and access community knowledge.

D6.1 – Ecosystem Software Platform with Underlying Software Repository, Digital Library and Media Archive

The objective of D6.1 is to make the Ecosystem software platform with underlying Software Repository, Digital Library and Media Archive available to the degree, that the RAGE project can start collecting content in the form of software assets, and documents of various media types. This paper describes the current state of the Ecosystem as of month 12 of the project, and documents the structure of the Ecosystem, individual components, integration strategies, and overall approach. The deliverable itself is the deployment of the described components, which is now available to collect and curate content. Whilst this version is not yet feature complete, full realization is expected within the next few months. Following this development, WP6 will continue to add features driven by the business models to be defined by WP7 later on in the project.

D9.5 – Exploitation Plan (version 1 of 3)

The RAGE Exploitation Plan is a living document, to be upgraded along the project lifecycle, supporting RAGE partners in defining how the results of the RAGE RIA will be used both in commercial and non-comercial settings. The Exploitation Plan covers the entire process from the definition of the business case for the RAGE Ecosystem to the creation of the sustainability conditions for its real-world operation beyond the H2020 project co-funding period. The Exploitation Plan will be published in three incremental versions, due at months 18, 36 and 42 of the project lifetime. This early stage version 1 of 3 is mainly devoted to: i. Setting-up the structure and the initial building blocks to be populated and completed in the future editions of the Exploitation Plan and to ii. providing additional guidance for market intelligence gathering, business modelling definition and validation, outreach and industry engagement and ultimately providing insights for the development, validation and evaluation of RAGE results across the project´s workplan execution. These tasks will in turn render suitable inputs to enhance the two future editions of the Exploitation Plan.

D5.5 – First Version Scenario Arrangement Document – round 1

This deliverable outlines the implementation plan for each of the first-round studies of the RAGE pilots. The main goal of these pilots is to perform a small-scale test of the RAGE games with end-users and intermediary stakeholders in five different non-leisure domains to guide the further development of the games for the final validation studies. At the same time the pilots implement the pre-testing of the research instruments and methodology for answering the main evaluation questions in the five areas of investigation identified in D8.1: 1) usability, 2) game experience, 3) learning effectiveness, 4) transfer effect and 5) pedagogical costs and benefits. Finally, the pilots are aimed at collecting preliminary results for a first formative evaluation of the games and game technologies, with the goal of feeding back useful information to development for the final versions of games and assets. The results of the first pilot will be compared with the results of the final evaluation studies to demonstrate improvements of the game and game effects from first to final version. A revision of the deliverable will be done in the next few months to produce the final arrangement document (D5.1, due at M21).

D3.5 – First Storytelling Framework

This document presents the first release of the project’s storytelling framework, which is composed by two assets. The purpose of this framework is to facilitate the use of interactive storytelling for the development of applied games. More precisely, the framework is meant to aid developers in the creation of game scenarios where both players and autonomous characters are playing an active role in a narrative that unfolds according to their actions. The document describes the current state for the assets that are part of this framework, also providing links to the source code of the assets as well as associated demonstrations and documentation. The primary audience for the contents of this deliverable are the game developers that will use the proposed framework in their development process. The information about the specific RAGE use cases that are using the framework is written in Deliverable 4.2.

D3.3 – First Social Gamification Assets

This deliverable is software, as such this document is abridged to be as succinct as possible, the extended descriptions and detailed documentation for the software are online. The document consists of two parts, part one describes the first bundle of social gamification assets developed in WP3, part two presents mock-ups of the RAGE ecosystem gamification. In addition to the software outline, included in part one is a short market analysis of existing gamification solutions, outline rationale for combining the three social gamification assets into one unified asset, and the branding exercise to make the assets more developer friendly.Online links to the source code, binaries, demo and documentation for the assets are provided. The combined assets offer game developers as well as a wide range of software developers the opportunity to readily enhance existing games or digital platforms with multiplayer gamification functionalities, catering for both competitive and cooperative game dynamics. The solution consist of a flexible client-server solution which can run either as a cloud-based service, serving many games or have specific instances for individual games as necessary.

D3.1 – First Bundle of Core Social Agency Assets

This deliverable presents and describes the first delivery of assets that are part of the core social agency bundle. In total, the bundle includes 16 assets, divided into 4 main categories. Each category is related to a type of challenge that developers of applied games are typically faced with and the aim of the included assets is to provide solutions to those challenges. The main goal of this document is to provide the reader with a description for each included asset, accompanied by links to their source code, distributable versions, demonstrations and documentation. A short discussion of what are the future steps for each asset is also given. The primary audience for the contents of this deliverable are the game developers, both inside and outside of the project, which can use this document as an official list of the current social agency assets and their associated resources. Note that the information about which RAGE use cases are using which of these assets is described in Deliverable 4.2.

D2.5 - First bundle of dashboard components

This document describes the core components to create customizable game analytics and dashboards: their present status; links to their full designs and downloadable versions; and how to configure them, and take advantage of the analytics visualizations and the underlying architecture of the platform. All the dashboard components are working with data collected using the xAPI data format that the RAGE project has developed in collaboration with ADL Co-Lab.

Extracting Patterns from Educational Traces via Clustering and Associated Quality Metrics

Clustering algorithms, pattern mining techniques and associated quality metrics emerged as reliable methods for modeling learners’ performance, comprehension and interaction in given educational scenarios. The specificity of available data such as missing values, extreme values or outliers, creates a challenge to extract significant user models from an educational perspective. In this paper we introduce a pattern detection mechanism with-in our data analytics tool based on k-means clustering and on SSE, silhouette, Dunn index and Xi-Beni index quality metrics. Experiments performed on a dataset obtained from our online e-learning platform show that the extracted interaction patterns were representative in classifying learners. Furthermore, the performed monitoring activities created a strong basis for generating automatic feedback to learners in terms of their course participation, while relying on their previous performance. In addition, our analysis introduces automatic triggers that highlight learners who will potentially fail the course, enabling tutors to take timely actions.

Classifying Written Texts Through Rhythmic Features

Rhythm analysis of written texts focuses on literary analysis and it mainly considers poetry. In this paper we investigate the relevance of rhythmic features for categorizing texts in prosaic form pertaining to different genres. Our contribution is threefold. First, we define a set of rhythmic features for written texts. Second, we extract these features from three corpora, of speeches, essays, and newspaper articles. Third, we perform feature selection by means of statistical analyses, and determine a subset of features which efficiently discriminates between the three genres. We find that using as little as eight rhythmic features, documents can be adequately assigned to a given genre with an accuracy of around 80 %, significantly higher than the 33 % baseline which results from random assignment.

Expressing Sentiments in Game Reviews

Opinion mining and sentiment analysis are important research areas of Natural Language Processing (NLP) tools and have become viable alternatives for automatically extracting the affective information found in texts. Our aim is to build an NLP model to analyze gamers’ sentiments and opinions expressed in a corpus of 9750 game reviews. A Principal Component Analysis using sentiment analysis features explained 51.2 % of the variance of the reviews and provides an integrated view of the major sentiment and topic related dimensions expressed in game reviews. A Discriminant Function Analysis based on the emerging components classified game reviews into positive, neutral and negative ratings with a 55 % accuracy.

ReaderBench goes Online: A Comprehension-Centered Framework for Educational Purposes

In this paper we introduce the online version of our ReaderBench framework, which includes multi-lingual comprehension-centered web services designed to address a wide range of individual and collaborative learning scenarios, as follows. First, students can be engaged in reading a course material, then eliciting their understanding of it; the reading strategies component provides an in-depth perspective of comprehension processes. Second, students can write an essay or a summary; the automated essay grading component provides them access to more than 200 textual complexity indices covering lexical, syntax, semantics and discourse structure measurements. Third, students can start discussing in a chat or a forum; the Computer Supported Collaborative Learning (CSCL) component provides indepth conversation analysis in terms of evaluating each member’s involvement in the CSCL environments. Eventually, the sentiment analysis, as well as the semantic models and topic mining components enable a clearer perspective in terms of learner’s points of view and of underlying interests.

Predicting Academic Performance Based on Students' Blog and Microblog Posts

This study investigates the degree to which textual complexity indices applied on students’ online contributions, corroborated with a longitudinal analysis performed on their weekly posts, predict academic performance. The source of student writing consists of blog and microblog posts, created in the context of a project-based learning scenario run on our eMUSE platform. Data is collected from six student cohorts, from six consecutive installments of the Web Applications Design course, comprising of 343 students. A significant model was obtained by relying on the textual complexity and longitudinal analysis indices, applied on the English contributions of 148 students that were actively involved in the undertaken projects.

Combining Taxonomies using Word2vec

Taxonomies have gained a broad usage in a variety of fields due to their extensibility, as well as their use for classification and knowledge organization. Of particular interest is the digital document management domain in which their hierarchical structure can be effectively employed in order to organize documents into content-specific categories. Common or standard taxonomies (e.g., the ACM Computing Classification System) contain concepts that are too general for conceptualizing specific knowledge domains. In this paper we introduce a novel automated approach that combines sub-trees from general taxonomies with specialized seed taxonomies by using specific Natural Language Processing techniques. We provide an extensible and generalizable model for combining taxonomies in the practical context of two very large European research projects. Because the manual combination of taxonomies by domain experts is a highly time consuming task, our model measures the semantic relatedness between concept labels in CBOW or skip-gram Word2vec vector spaces. A preliminary quantitative evaluation of the resulting taxonomies is performed after applying a greedy algorithm with incremental thresholds used for matching and combining topic labels.

Predicting Student Performance and Differences in Learning Styles based on Textual Complexity Indices applied on Blog and Microblog Posts

Social media tools are increasingly popular in Computer Supported Collaborative Learning and the analysis of students' contributions on these tools is an emerging research direction. Previous studies have mainly focused on examining quantitative behavior indicators on social media tools. In contrast, the approach proposed in this paper relies on the actual content analysis of each student's contributions in a learning environment. More specifically, in this study, textual complexity analysis is applied to investigate how student's writing style on social media tools can be used to predict their academic performance and their learning style. Multiple textual complexity indices are used for analyzing the blog and microblog posts of 27 students engaged in a project-based learning activity. The preliminary results of this pilot study are encouraging, with several indexes predictive of student grades and/or learning styles.