Dimoklis Despotakis

Taming digital traces for informal learning: a semantic-driven approach

Modern learning models require linking experiences in training environments with experiences in the real-world. However, data about real-world experiences is notoriously hard to collect. Social spaces bring new opportunities to tackle this challenge, supplying digital traces where people talk about their real-world experiences. These traces can become valuable resource, especially in ill-defined domains that embed multiple interpretations. The paper presents a unique approach to aggregate content from social spaces into a semantic-enriched data browser to facilitate informal learning in ill-defined domains. This work pioneers a new way to exploit digital traces about real-world experiences as authentic examples in informal learning contexts. An exploratory study is used to determine both strengths and areas needing attention. The results suggest that semantics can be successfully used in social spaces for informal learning – especially when combined with carefully designed nudges.

Exploring exploratory search: a user study with linked semantic data

The maturation of semantic technologies and the growing popularity of the Linked Open Data (LOD) cloud make it possible to expose linked semantic data sets to end users in order to empower a range of analytical tasks taking advantage of knowledge integration and semantic linking. Linked semantic data appears to offer a great potential for exploratory search, which is open-ended, multi-faceted, and iterative in nature. However, there is limited insight into how browsing through linked semantic data sets can support exploratory search. This paper presents a user study with a uni-focal semantic browsing interface for exploratory search through several data sets linked via domain ontologies. The study, which is qualitative and exploratory in nature and uses music as an illustrative domain, examines (i) obstacles and challenges related to user exploratory search in LOD and (ii) the serendipitous learning effect and the role semantics plays in that. The approach and lessons learnt can benefit future human factor studies to evaluate interactive exploration of linked semantic data, as well as technology developers to become aware of issues that have to be addressed in to facilitate exploratory search with LOD.

Assisting user browsing over linked data: requirements elicitation with a user study

There are growing arguments that linked data technologies can be utilised to enable user-oriented exploratory search systems for the future Internet. Recently, search over linked data has been studied in different domains and contexts. However, there is still limited insight into how conventional semantic browsers over linked data can be extended to empower exploratory search, which is open-ended, multi-faceted and iterative in nature. Empirical user studies in representative domains can identify problems and elicit requirements for innovative functionality to assist user exploration. This paper presents such an approach --- a user study with a uni-focal semantic data browser over several datasets linked via domain ontologies is used to inform what intelligent features are needed in order to assist exploratory search through linked data. We report main problems experienced by users while conducting exploratory search tasks, based on which requirements for algorithmic support to address the observed issues are elicited. A semantic signposting approach for extending a semantic data browser is proposed as a way to address the derived requirements.

Multi-perspective context modelling to augment adaptation in simulated learning environments

Simulated environments, where learners are involved in simulated situations that resemble actual activities, gain a growing popularity in professional training, and provide powerful experiential learning tools for developing soft skills in ill-defined domains[1]. Adaptation and personalization will play a key role in these environments[2].

User Interaction with Linked Data: An Exploratory Search Approach

It is becoming increasingly popular to expose government and citywide sensor data as linked data. Linked data appears to offer a great potential for exploratory search in supporting smart city goals of helping users to learn and make sense of complex and heterogeneous data. However, there are no systematic user studies to provide an insight of how browsing through linked data can support exploratory search. This paper presents a user study that draws on methodological and empirical underpinning from relevant exploratory search studies. The authors have developed a linked data browser that provides an interface for user browsing through several datasets linked via domain ontologies. In a systematic study that is qualitative and exploratory in nature, they have been able to get an insight on central issues related to exploratory search and browsing through linked data. The study identifies obstacles and challenges related to exploratory search using linked data and draws heuristics for future improvements. The authors also report main problems experienced by users while conducting exploratory search tasks, based on which requirements for algorithmic support to address the observed issues are elicited. The approach and lessons learnt can facilitate future work in browsing of linked data, and points at further issues that have to be addressed.

Identifying relevant youtube comments to derive socially augmented user models: a semantically enriched machine learning approach

Media resources in social Web spaces trigger social interactions, as they consist of motivating means to create and exchange user-generated content. The massive social content could provide rich resources towards deriving social profiles to augment user models and improve adaptation in simulated learning environments. However, potentially valuable social contributions can be buried within highly noisy content that is irrelevant or spam. This paper sketches a research roadmap toward augmenting user models with key user characteristics derived from social content. It then focuses on the first step: identifying relevant content to create data corpus about a specific activity. A novel, semantically enriched machine learning approach to filter out the noisy content from social media is described. An application on public comments in YouTube on job interview videos has been made to evaluate the approach. Evaluation results, which illustrate the ability of the approach to filter noise and identify relevant social media content, are analysed.

Making Sense of Linked Data: A Semantic Exploration Approach

There are growing arguments that Linked Data technologies can be utilised to enable user-oriented exploratory search systems for the future Internet. Recently, search over Linked Data has been studied in different domains and contexts. However, there is still limited insight into how conventional semantic browsers over Linked Data can be extended to empower exploratory search, which is open-ended, multi-faceted and iterative in nature. Empirical user studies in representative domains can identify problems and elicit requirements for innovative functionality to assist user exploration. This chapter presents such an approach—a user study with a unifocal semantic data browser over several datasets linked via domain ontologies is used to inform what intelligent features are needed in order to assist exploratory search through Linked Data. We report main problems experienced by users while conducting exploratory search tasks, based on which requirements for algorithmic support to address the observed issues are elicited. A semantic signposting approach for extending a semantic data browser is proposed as a way to address the derived requirements.

Semantic Social Sensing for Improving Simulation Environments for Learning

The rapidly growing learning simulations market calls urgently for innovative ways to facilitate the simulation design process [1],[2]. Social spaces can provide an extensive source of reports on individuals experiences and their real-world contexts that may be exploited for the purpose of identifying relevant content and evaluating the quality of a simulation. To realise this potential, appropriate ways to make sense of user generated content UGC are needed. This work presents a novel approach, called semantic social sensing SSS, which exploits ontologies and semantic augmentation combined with discourse analysis uncovering intentions behind the user comments. We have developed two SSS instruments enabling analysis of UGC --- a a framework for automatic semantic analysis for capturing viewpoints ViewS, which utilises ontologies and semantic tagging and enrichment and enables visual exploration of the conceptual spaces associated with UGC [3]; and b a schema for discourse analysis to identify intentions useful for simulator design [2] and inspired by research analysing communicative functions of user contributions in collaborative settings [4].