BOTTARI: How to offer innovative services listening to the Social Media

BOTTARI: How to offer innovative services

listening to the Social Media

Emanuele Della Valle DEI - Politecnico di Milano

emanuele.dellavalle@polimi.ithttp://emanueledellavalle.org

• Introduction

• Architecture

• Components

• Query Processing

• Evaluation– Efficacy– Efficiency

• Conclusions

Agenda

227.02.2012 - Workshop di Senso Comune, Trento, Italy

Introduction

A stream of live opinions

• Micro-posts carry the live opinion of social media users about topics and points of interest.

• In 2011, an average of three million tweets per day was posted in Seoul.

• A large number of these micro-posts are about restaurants, bars, coffees and many other semi-public points of interest (POIs) in the city.

• Let us consider, Insadong district with its +200 restaurants

Introduction

Seoul’s stream of live opinions

Number of tweets per day related to Insadong’srestaurants

Insadong’s restaurantsordered by decreasingfrequency of tweets

• Trusting this collective opinion, can novel commercial and social services be considered?

• The case of BOTTARI

Introduction

A commercial/social opportunity?

http://www.youtube.com/watch?v=XGOKe_lhSks

• An augmented reality application for personalized recommendation of restaurants in Insadong (Seoul)

Introduction

What have you seen?

• Yes and no!

• Same use case

• BOTTARI listens to the social media

Introduction

Yet another ?

outout

Query RewriterQuery Rewriter

Query Evaluator

Machine LearningMachine Learning

Streaming ProcessorStreaming Processor

Geo Filtering

Geo-spatial KB

Social Media Analyzer

Architecture

Android Client

27.02.2012 - Workshop di Senso Comune, Trento, Italy 8

outout

Query Evaluator

Semantic Stream

Processor

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

Architecture

Geo-Spatial KB

outout

Query Evaluator

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

PUSH: Data Initiated

ArchitecturePUSH Segment – Data Initiated

Query Rewriter

Query Evaluator

Machine Learning

SemanticStream

Processor

SemanticStream

Processor

Geo Filtering

Geo-spatial KB

ArchitecturePULL Segment – Query Initiated

Query Rewriter

Query Evaluator

Machine Learning

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

ArchitectureThe Entire BOTTARI System

Components

SOR - Geo-Spatial KB

Components

Micro-post

MorphologicallyAnalyzable?

Rule based Analysis

Auto generated rules

Learneddocuments

Syllable KernelSyllable Kernel

Sentiment of the tweet

Yes No

• Precision tests:– Auto-generated

rules ≈ 70%

– Manually-coded rules ≈ 90%

– Syllable kernel ≈ 50~60%

• Our target > 85%

Components

Semantic Stream Processor

• SUNS (Statistical Unit Node Sets)– A machine learning framework for inductive

materialization• Detects interesting data patterns• Predics RDF-triples

– i.e., which restaurant a user will tweet positively about

– Caractheristics • Capability to deal with sparse, high-dimensional and

incomplete data• Multivariate latent space based approach• Modularized approach for easily integrating contextual

information

Components

Machine Learning Component

Query Rewriter

Query Evaluator

Machine Learning

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

Query ProcessingAn Ontology-based Approach

SELECT DISTINCT ?poi ?name ?lat ?long ?numPos ?prob WHERE { ?poi a ns:NamedPlace ; ns:name ?name ; geo:lat ?lat ; geo:long ?long . FILTER (f:within_distance(37.5, 126.9, ?lat, ?long, 200)) FILTER (f:dest_point_viewing(37.5, 126.9, ?lat, ?long, 90, 200)) { :someUser sioc:creator_of ?tweet . ?tweet twd:talksAboutPositively ?poi . WITH PROBABILITY ?prob ENSURE PROBABILITY [0.5..1) } ?poi twd:numberOfPositiveTweets ?numPos . } ORDER BY DESC(?numPos), ?prob, f:distance(37.5, 126.9, ?lat, ?long)LIMIT 10

GEO-SPATIAL FILTER

RECCOMENDENDATION

REPUTATION

Query Processing

An Example Query

outQuery Evaluator

Query Rewriter

Machine Learning

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

The issued query is rewritten in three queries; one for each

run time component

Query ProcessingThe Input Received is Rewritten

outQuery Evaluator

Query Rewriter

Machine Learning

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

Generates personalized recommendations

Query ProcessingEach Component Answers

outQuery Evaluator

Query Rewriter

Machine Learning

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

Gets trends in restaurants’ social reputation P

outQuery Evaluator

Query Rewriter

Machine Learning

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

Gets restaurants

close to user location

outQuery Evaluator

Joins results and returns

Query Rewriter

Machine Learning

Semantic Stream

Processor

Geo Filtering

Geo-spatial KB

Query ProcessingResults Are Joined and Returned

Evaluation

Efficacy – High Accuracy

Evaluation

Efficacy – Remembering 90 Days is Enough

Evaluation

Efficiency – High Throughput

• End-user application

• Attractive and functional interface

• Real-world dynamic data

• Fully based on Semantic Web technologies– RDF as common data format between heterogeneous

components– SPARQL as query language

• Rigorously evaluated– Effective– High throughput for handling dynamic data

• Commercial Potential

Conclusions

• Tony Lee, Seonho Kim (SALTLUX)– Android Application – Social Media Analyzer– Tweets and restaurant descriptiond for Insadong

• Marco Balduini (PoliMi)– Semantic Stream Processor

• Irene Celino, Daniele Dell’Aglio (CEFRIEL)– LarKC workflows– Ontology

• Volker Tresp, Yi Huang (SIEMENS)– Machine Learning component

Credits

BOTTARI is a joint work with

Thank You! Questions?

Much More to Come!Keep an eye on

http://www.streamreasoning.org

BOTTARI: How to offer innovative services

listening to the Social Media

Emanuele Della Valle DEI - Politecnico di Milano

emanuele.dellavalle@polimi.ithttp://emanueledellavalle.org

BOTTARI: How to offer innovative services listening to the Social Media

Business

Transcript of BOTTARI: How to offer innovative services listening to the Social Media

Listening and listening assessment

Session 4 Listening to the stakeholders of innovative medicinal … · Session 4 Listening to the stakeholders of innovative medicinal products. >The Patient perspective Martine Pergent,

Listening and Nonverbal Communication. Listening.

LIGHTING - bottari.czbottari.cz/document/pdf/bottari/9_ILLUMINAZIONE.pdf · LIGHTING - ILLUMINAZIONE - ILUMINACIÓN 146 30125X LAMPADA H7 12V • Halogen bulb H7 12V 55W • Lampada

Risk Solutions User Forum Jeff Bottari, VP Risk Solutions Group CheckFree October 24, 2007.

BC Listening (20656 - Activated, Traditional) · *6854271086* Listening Listening Listening Listening Listening Listening Listening IELTS Listening Answer Sheet Listening Total: Marker

We’re listening. - LibQUAL · 2014-08-22 · We’re listening. We’re listening. We’re listening. We’re listening. We’re listening. Invest 10 minutes of your time for an

IMPROVING HOW LISTENING SKILLS ARE TAUGHT IN · PDF fileIMPROVING HOW LISTENING SKILLS ARE TAUGHT ... lack of innovative approaches to teaching ... how to improve teaching listening

Turbo Listening - Clover Sitesstorage.cloversites.com/agcoaching/documents/Turbo...Turbo Listening 1. Distinctions between listening and active listening 2. Active Listening Definition,

To our class. Grade 11 C. Listening Pre-listening While-listening Post-listening.

Elena Bottari

LISTENING (Definition, Importance & Effective Listening)

Listening to Parents Listening Partnerships for Parents · Listening to Parents Listening Partnerships for Parents ... Listening to Parents Listening Partnerships for ... you will

6/2015 Listening Education - International Listening … Listening Education, Vol 6... · International Listening Association Listening Education 6/2015 . 2 Listening Education 6/2015

The basics Listening activities. Listening Activities Three stages 1. Pre listening 2. During listening 3. Post listening Activate background knowledge.

CHAPTER - 4 COMMUNICATION SKILLSnewhorizonindia.edu/nhc_kasturinagar/wp-content/uploads/...TYPES OF LISTENING •ACTIVE LISTENING •PASSIVE LISTENING •SELECTIVE LISTENING •EMPATHETIC

Effective Listening Strategies with Tactics for Listening · · 2015-11-16Effective Listening Strategies with Tactics for Listening Rob Peacock ... TOEIC Listening Test Part 3:

AT C E S innovaTive Cs2 - · PDF fileThiel’s innovaTive Cs2.7 NEW ... buddy Holly bob dylan chet baker + New High-Res ... to nearly 35Hz in the best location in my listening room

“Hearing Loops” Provide Effective Communications at ... · Audio Directions (by Emcom Systems) is an industry leader in assistive listening technology, providing innovative solutions

Devoted to Luang Por - cd1.amaravati.org · Listening moon Listening Is the listening moon Within Listening Is the listening tomb Without Listening Listening So please don’t shout

BC Listening (20656 - Activated, Traditional) · 6854271086 Listening Listening Listening Listening Listening Listening Listening IELTS Listening Answer Sheet Listening Total: Marker