integrating digital traces into a semantic enriched data
TRANSCRIPT
INTEGRATING DIGITAL TRACES INTO A SEMANTIC-ENRICHED DATA CLOUD FOR INFORMAL LEARNING
Vania Dimitrova, Dhaval Thakker, Lydia Lau
Outline
Motivation and bigger picture Aggregating Digital traces into Semantic-
enriched data cloud Semantic Data Browser Exploratory Evaluation Conclusions
Modern learning models require linking experience in training environments with experience in the real-world.
Real-world experiences are hard to collect Social media brings new opportunities to
tackle this challenge, supplying digital traces Exploiting social content as a source for
experiential learning is being investigated in Immersive Reflective Experience based Adaptive Learning (ImREAL)
Motivation
http://imreal-project.eu/
Digital Traces
broad, authentic, gradually increasing and
up-to-date digital examples
Hard to specify and often require multiple interpretations and viewpoints.
Soft skills – communicating, planning, managing, advising, negotiating.
Highly demanded Modern informal learning
environments for soft skills can exploit digital traces to provide learning situations linked to real world experience by peers (other learners) or tutors.
Ill-Defined domains
To realise this vision, novel architectures are needed which use: robust and cost-effective ways to retrieve, create, aggregate, organise, and exploit Digital Traces in learning situations; in other words, to tame Digital Traces for informal learning.
By combining major advancements in semantic web : semantic augmentation, semantic query, relatedness, similarity, summarisation, etc.
Role of Semantic Web Technologies
Processing Pipeline
Digital Traces
Collection
Ontology Underpinning
Semantic Augmentation
& Query
Browsing & Interaction
Bespoke Ontologies & Linked Data Cloud
Processing Pipeline – DTs collection
Digital Traces
Collection
Ontology Underpinning
Semantic Augmentation
& Query
Browsing & Interaction
Bespoke Ontologies & Linked Data Cloud
•Availability of Social Web APIs•Noise filtration mechanisms*•Role of tutors/trainers in setting gold standard**
* Ammari, A., Lau, L. Dimitrova, V. Deriving Group Profiles from social media, LAK 2012
** Redecker, C. et al. Learning 2.0- the impact of social media on learning in Europe, Policy Brief, European Commission, JRC, 2010
Processing Pipeline – Semantics
Digital Traces
Collection
Ontology Underpinning
Semantic Augmentation
& Query
Browsing & Interaction
Bespoke Ontologies & Linked Data Cloud
Social WebActivityTheory
on a UseCase
Use CaseActivity Model
other relevant ontologies
Multi-layered Activity Modelling Ontology
(AMOn) forInterpersonal Communications
Stage 2: Activity Modelling Enrichment using Semantics
Analysis
Logical Encoding
Stage 1: Activity Modelling on Interpersonal Communication
Stage 3: Providing Access to Real World Experiences
Social Web
Semantic Services:
Augmentation,Query
WN-AffectBody
Language
Processing Pipeline - Semantics
Story Boarding
Handshake BL
Body language
Handshake
is almost always best. An authority handshake should be reserved for when you wish to show you are in charge.
handshake
Purpose : Generic service designed to link content with the concepts from the ontological knowledge bases in order to fully benefit from the reasoning capabilities of semantic technologies.
Simulators
Semantic Linking
Information
Extraction Ontology
AMOn
Semantic Repository
Components: • Information Extraction: Finding
mentions of entities in text• Semantic Linking: between entity
mentions and ontologies, linked data
• Semantic Repository: forward chaining repository for semantic expansion
• Ontologies: AMOn & External ontologiesImplementation:
• RESTful interface for easy integration
• Contribution to the semantic augmentation in the IPC domain
Semantic Augmentation Service
Purpose : Generic service for querying and browsing using semantically augmented content. In I-CAW, it allows searching of socially and locally authored data for real-world activities from the domain of interest
Concept Frequency
ConceptFiltering
Semantic Relatednes
s
ContentFiltering
Components: • Concept Filtering: Identify matching
concepts and relevant information• Content Filtering: Identify matching
contents and relevant information• Concept Frequency: CF/IDF analysis• Semantic Relatedness: Content &
concept relatedness
Implementation: • RESTful interface for easy
integration, integrated with Storyboard
• Contribution to the semantic browsing of content and knowledge bases
BrowsingTag Cloud
Matching ContentRelated Content
Term(s), Concept(s)
Simulators
Semantic Query Service
LearnerTrainer
Exploratory Study
Domain : Job Interview Digital Traces: User comments from
YouTube - cleaned from filtration, stories from blog-like environment by ImREAL volunteers
ParticipantsGroup 1: Interviewers
Group 2: Applicants
Participant ID P2 P3 P4 P5 P10 P1 P6 P7 P8 P9
No. of Interviews
as an interviewer
10-15
10-15
10-15 >15 >15 0 0 0 0 1-5
No. of interviews
as an applicant
10-15
10-15
10-15 >15
5-10 1-5 1-5 1-5
5-10
5-10
Participants particularly liked the authenticity of the content:
“Examples are the beauty of system – I will learn from examples [p10]”
“Anything that facilitates the preparation of training material and provides real world examples to backup training is very helpful [p5]”
Which probed them to: Further reflect on their experiences, and in some
cases help articulate what they had been doing intuitively
Provide their viewpoints (due to culture, environment, tacit knowledge) – acted as stimuli
Sense the diversity or consensus on the selected topic
Exploratory Study: Good things about DTs
Exploratory Study: Issues with DTs Issues requiring attention:
Two most experienced interviewers(p5 and p10) commented that some content could be mistaken as the norm.
For instance, a comment associated with a video stated “The interviewer has his hands in front of him, which indicates that he is concentrating and not fidgeting...”. P5 and P10 stressed that inexperienced users may see a comment in isolation and believe it would be valid in all situations
It was suggested that short comments could be augmented with contextual information to assist the assessment of the credibility of the different viewpoints
Conclusions
Social spaces bring new opportunities , i.e. as a source of diverse range of real-world experiences. Initial signs are encouraging – digital traces as a
source of authentic examples and stimuli Further work is needed to capitalise on new
opportunities brought by social content Semantics technologies provide apparatus
for taming digital traces Further work is needed to turn semantic
browsing into informal learning.
Thank You!
[email protected]://www.imreal-project.eu/