Presentation is loading. Please wait.

Presentation is loading. Please wait.

Miha Grčar (Department of Knowledge Technologies, Jožef Stefan Institute) & FIRST Consortium M12 scenario: Early prototype demo Luxembourg, Nov 2011.

Similar presentations


Presentation on theme: "Miha Grčar (Department of Knowledge Technologies, Jožef Stefan Institute) & FIRST Consortium M12 scenario: Early prototype demo Luxembourg, Nov 2011."— Presentation transcript:

1 Miha Grčar (Department of Knowledge Technologies, Jožef Stefan Institute) & FIRST Consortium M12 scenario: Early prototype demo Luxembourg, Nov 2011

2 Outline We will show two integrated prototypes Twitter sentiment analysis prototype Sentiment extraction prototype The aim is to… Give a better idea of the overall FIRST process Give a hint of the final “product” from the technological perspective Demonstrate the collaboration between partners (integration efforts) Luxembourg, Nov 2011 FIRST Y1 Review Meeting 2

3 Twitter Sentiment Demo Luxembourg, Nov 2011 Architecture, Integration & Scaling Strategy Architecture, Integration & Scaling Strategy Management WP10 WP2 & WP7 Dissemination & Exploitation WP9 WP3 WP4 WP6 Ontology Infrastructure Ontology Infrastructure Information Extraction Information Extraction Sentiment Analysis Sentiment Analysis Decision Support Infrastructure Decision Support Infrastructure Domain-independent GUI (Open Source) Domain-independent GUI (Open Source) Information Integration Data, Information & Knowledge Base WP5 WP1 & WP8 UC#1 Market Surveillance UC#1 Market Surveillance UC#2 Reputational Risk management UC#2 Reputational Risk management UC#3 Online Retail Brokerage UC#3 Online Retail Brokerage Data Acquisition Data Acquisition Data Acquisition FIRST Y1 Review Meeting 3 Sentiment Analysis Decision Support Infrastructure Domain-independent GUI (Open Source) Information Integration Acquisition of Tweets Sentiment Classification Active Learning & Visualization Database of Tweets Web-based Infrastructure

4 Basic Concepts Sentiment classification Active learning Luxembourg, Nov 2011 FIRST Y1 Review Meeting 4

5 Sentiment Classification Labeled examples Build model (train classifier) Classify unlabeled examples Luxembourg, Nov 2011 FIRST Y1 Review Meeting POS Financial markets are now officially open :) POS market intelligence GMI Interactive and Mintel Win ARF Great Minds Award for Quality in Research POS $AAPL : trust me -- AAPL will soar tomorrow NEG Oh how I miss the days with GBP was at least 2 times the AUD. Sterling forecast to hit all-time lows soon NEG omg! did you know BORDERS closed?! they went bankrupt last month and closed!! awww, too bad! i love borders!! NEG @aekins that's just too bad Labeled Examples Labeled Examples Training Algorithm Training Algorithm Classification Model Classification Model Classification Algorithm Classification Algorithm Unlabeled Examples Unlabeled Examples Predictions (Labels) Predictions (Labels) So Nickelodeon filed for bankruptcy and announced that the next Kids Choice Awards will be it's last. NEG Classification Model Classification Model 5

6 Active Learning Labeling examples manually is expensive Active learning reduces this cost Experts provide labels only for a (small) subset of examples Examples in this subset are carefully chosen to produce a classifier that is “as accurate as possible” Luxembourg, Nov 2011 FIRST Y1 Review Meeting 6

7 Document space (tweets) Active Learning 7 Luxembourg, Nov 2011 FIRST Y1 Review Meeting

8 Document space (reality) Active Learning Negative sentiment Positive sentiment Optimal hyperplane Luxembourg, Nov 2011 8 FIRST Y1 Review Meeting

9 Document space (initial guess) Active Learning Luxembourg, Nov 2011 9 FIRST Y1 Review Meeting

10 Document space (refinement) Active Learning Luxembourg, Nov 2011 10 FIRST Y1 Review Meeting

11 Document space (refinement) Active Learning Luxembourg, Nov 2011 11 FIRST Y1 Review Meeting

12 Document space (almost there…) Active Learning Luxembourg, Nov 2011 12 FIRST Y1 Review Meeting

13 Acquired Tweets Active Learning Workflow Luxembourg, Nov 2011 FIRST Y1 Review Meeting Twitter API Language Detector Near- Duplicate Remover Part of Speech Tagger Training Algorithm Classification Model Tweets Labeled Dataset Twitter API Preprocessing Classifier Classification Model Twitter Sentiment Results User Query 13 Client Active Learning Demo video (3:00)

14 Early Integrated Prototype Luxembourg, Nov 2011 Architecture, Integration & Scaling Strategy Architecture, Integration & Scaling Strategy Management WP10 WP2 & WP7 Dissemination & Exploitation WP9 WP3 WP4 WP6 Ontology Infrastructure Ontology Infrastructure Information Extraction Information Extraction Sentiment Analysis Sentiment Analysis Decision Support Infrastructure Decision Support Infrastructure Information Integration Data, Information & Knowledge Base WP5 WP1 & WP8 UC#1 Market Surveillance UC#1 Market Surveillance UC#2 Reputational Risk management UC#2 Reputational Risk management UC#3 Online Retail Brokerage UC#3 Online Retail Brokerage Data Acquisition Data Acquisition Data Acquisition FIRST Y1 Review Meeting 14 Sentiment Analysis Information Integration Information Extraction Ontology Infrastructure Historical Data ZeroMQ Channel Decision Support Infrastructure Visualization Domain-independent GUI (Open Source) Domain-independent GUI (Open Source) Domain-independent GUI (Open Source) Stream Simulator Web-based Infrastructure

15 Early Integrated Prototype Luxembourg, Nov 2011 FIRST Y1 Review Meeting Data Stream Simulator ZeroMQ Channel 15 Sentiment Extractor ZeroMQ Channel Historical Data (Documents) HTTP Push Web Server Client (Browser) Client (Browser) Client (Browser) Client (Browser) Client (Browser) Client (Browser) Documents (XML) Sentiment Index (Numbers) Java C# JavaScript WP3 WP4 WP2/7 WP5 WP2/7 WP6 Demo video (1:00)

16 Concluding Remarks Effortless integration of data acquisition, sentiment extraction, and Web-based interface First “signs of usefulness” for the financial domain Relationship to UC#2 (reputation) and UC#3 (retail brokerage) Luxembourg, Nov 2011 FIRST Y1 Review Meeting 16


Download ppt "Miha Grčar (Department of Knowledge Technologies, Jožef Stefan Institute) & FIRST Consortium M12 scenario: Early prototype demo Luxembourg, Nov 2011."

Similar presentations


Ads by Google