TechEvent Customer Project "Trend-Analytics"

BASLE BERN BRUGG DÜSSELDORF FRANKFURT A.M. FREIBURG I.BR. GENEVA
HAMBURG COPENHAGEN LAUSANNE MUNICH STUTTGART VIENNA ZURICH
Customer Project "Trend-Analytics"
Data Analytics & Semantic Web
Olaf Nimz
Martin Zablocki

Agenda
Customer Project "Trend-Analytics"2 14.09.2018
1. Introduction (short repetition of Part 1)
2. Data Analytics
3. Demo of Fraunhofer Trend-Analytics Platform
4. Semantic Web Technologies
5. Demo Knowledge Graphs

Introduction

Introduction
Research project for the automatic search,
analysis, and evaluation of sector specific
trend indicators in online publications
Cooperation with the Fraunhofer Institute
and the Technische Hochschule Nuremberg
Develop a Trend-Analytics platform that enables users to
– follow developments in the field of new technologies in a targeted manner
– react adequately to trends and market changes
martechtoday.com, New B2B analytics platform called Proof

Challenges
Research on modern machine-
learning algorithms & Semantic Web
Technologies
Identify trends and innovation
opportunities in different domains
Start by using a relatively small
number of high quality data, e.g.
RSS feeds
Permanently optimizing quantity and
quality of analytics
https://irishadvantage.com/news/irish-companies-making-iot-opportunity/

Overview Trend-Analytics Platform
Data Collection
– Implement crawling mechanism
– Implement database (e.g. in Azure)
– Create administration interface (web)
– Identify (manually) high quality data (RSS-Feeds & Articles)
Data Analysis
– Evaluate existing machine learning techniques
– E.g. Unsupervised Learning, Supervised, …
– Investigate Semantic Web Technologies
Data Presentation & Interpretation
– Create a Web Interface and illustrate the results
– Interpret results

Data Analytics

Word Embeddings
Word embedding is a technique that treats words as vectors
whose relative similarities correlate with semantic similarity.
Measuring similarity between vectors is possible using
measures such as cosine similarity.
So, when we subtract the vector of the word man from
the vector of the word woman, then its cosine distance
would be close to the distance between the word queen
minus the word king
https://www.oreilly.com/learning/capturing-semantic-meanings-using-deep-learning

Word2vec
Word2vec
Continuous Bag of Words (CBOW)
Model predicts the current word from
a window of surrounding context
words.
Same approach as recommender
systems with collaborative filtering.
(Customer => Item)
Instead of computing and storing large amounts of data, we create a neural network
model that will be able to learn the relationship between the words and do it efficiently.
https://www.oreilly.com/learning/capturing-semantic-meanings-using-deep-learning

Topic model
statistical model for discovering the abstract "topics" that occur in a collection of
documents. It captures intuition about frequency of words in a mathematical framework.
Li et al. Energies 2017, 10(11), 1913

Cluster of Term Frequencies
Latent Dirichlet Allocation
TF*IDF (inverse document freq.)
Reduced to a vector space of only
1000 dimensions
https://en.wikipedia.org/wiki/Latent_Dirichlet_allocation

Demo Trend-Analytics Platform

Semantic Web

Semantic Web – a vision in 2001
Semantic Web, a visionary concept proposed in 2001 by
Sir Tim Berners-Lee, the inventor of the World Wide Web
– “I have a dream for the Web [in which computers] become
capable of analyzing all the data on the Web – the content, links,
and transactions between people and computers. ..”
Sir Tim Berners-Lee, fossbytes.com, 2016
Amazon illustrates Knowledge
Graph in Neptune

Semantic Web now
Linking Open Data cloud
diagram showing 1.163 highly
interconnected datasets
(http://lod-cloud.net)

Semantic Data Enrichment for Trend-Analytics
headlines,
abstracts,
articles
Storage Entity detection
Spotting Candidate
Selection
Disambi-
guation
Filtering
Sets of
matched
resources
Semantic
Querying
Federated
Querying
Filtering
Storage
RDBMS RDBMS
Specific metadata
or neighborhood
Knowledge
Graph

headlines,
abstracts,
articles
Spotting Candidate
Selection
Disambi-
guation
Filtering
Sets of
matched
resources
Semantic
Querying
Federated
Querying
Filtering
Storage
RDBMS RDBMS
Specific metadata
or neighborhood
Knowledge
Graph

headlines,
abstracts,
articles
Spotting Candidate
Selection
Disambi-
guation
Filtering
Sets of
matched
resources
Semantic
Querying
Federated
Querying
Filtering
Storage
RDBMS RDBMS
Specific metadata
or neighborhood
Knowledge
Graph
DBpedia
Spotlight
DBpedia
SPARQL
Endpoint
DBpedia
talend talend
Relational
Databases
Relational
Databases

Next Steps
Understanding data using Knowledge Graphs
– Pull identified entities through to the user interface
and provide additional meta information on displayed
terms (e.g. as popups, hover-links, …)
– Objective: Improve the user's understanding of the
results, e.g. what is meant by a specific term?
Complex Ontology-based Data Enrichment
– Develop a domain-specific ontology which integerates with Knowledge Graphs
– Objective: Restrict search space in Knowledge Graphs & hide not relevant entities
– Requires extensive use of Semantic Web technologies and semantic data
modeling (TripleStores, RDF, RDF-S, OWL, …)
https://www.w3.org/TR/rdf11-primer/

Demo Knowledge Graphs

Demo: Semantic Data Enrichment
DBpedia Spotlight
https://www.dbpedia-spotlight.org/demo/
Nokia and Zain Saudi Arabia have taken a significant step towards the creation of an
IoT ecosystem in the Kingdom of Saudi Arabia with the successful trial of NB-IoT
technology at a live site in Mina area of Makkah Province.
Nokia and Zain Saudi Arabia have taken a significant step towards the creation of
an IoT ecosystem in the Kingdom of Saudi Arabia with the successful trial of NB-
IoT technology at a live site in Mina area of Makkah Province.

Demo: Semantic Data Enrichment (2)
Wikidata
https://query.wikidata.org/
https://www.wikidata.org/wiki/Q1418 (Nokia)
https://www.wikidata.org/wiki/Q851 (Saudi Arabia)
Wikidata Graph Builder
https://angryloki.github.io/wikidata-graph-builder/
https://angryloki.github.io/wikidata-graph-
builder/?property=P355&item=Q1418&iterations=8&mode=undirected
Metaphactory
https://wikidata.metaphacts.com/resource/app:Start
https://wikidata.metaphacts.com/resource/wd:Q1418

Questions & Answers…
Dr. Olaf Nimz
Principal Consultant
Olaf.Nimz@trivadis.com
14.09.2018 Customer Project "Analytical Data Lake"24
Dr. Martin Zablocki
Consultant
Martin.Zablocki@trivadis.com

TechEvent Customer Project "Trend-Analytics"

More Related Content

What's hot (20)

Similar to TechEvent Customer Project "Trend-Analytics" (20)

More from Trivadis (20)

Recently uploaded (20)

TechEvent Customer Project "Trend-Analytics"